The right way to Write a Good Spec for AI Brokers – O’Reilly

This submit first appeared on Addy Osmani’s Elevate Substack e-newsletter and is being republished right here with the creator’s permission.

TL;DR: Intention for a transparent spec overlaying simply sufficient nuance (this will likely embody construction, type, testing, boundaries. . .) to information the AI with out overwhelming it. Break giant duties into smaller ones versus conserving every thing in a single giant immediate. Plan first in read-only mode, then execute and iterate repeatedly.

“I’ve heard lots about writing good specs for AI brokers, however haven’t discovered a stable framework but. I might write a spec that rivals an RFC, however sooner or later the context is just too giant and the mannequin breaks down.”

Many builders share this frustration. Merely throwing a large spec at an AI agent doesn’t work—context window limits and the mannequin’s “consideration price range” get in the best way. The secret is to jot down good specs: paperwork that information the agent clearly, keep inside sensible context sizes, and evolve with the venture. This information distills greatest practices from my use of coding brokers together with Claude Code and Gemini CLI right into a framework for spec-writing that retains your AI brokers centered and productive.

We’ll cowl 5 ideas for excellent AI agent specs, every beginning with a bolded takeaway.

1. Begin with a Excessive-Degree Imaginative and prescient and Let the AI Draft the Particulars

Kick off your venture with a concise high-level spec, then have the AI develop it into an in depth plan.

As a substitute of overengineering upfront, start with a transparent purpose assertion and some core necessities. Deal with this as a “product temporary” and let the agent generate a extra elaborate spec from it. This leverages the AI’s power in elaboration whilst you keep management of the path. This works effectively until you already really feel you may have very particular technical necessities that have to be met from the beginning.

Why this works: LLM-based brokers excel at fleshing out particulars when given a stable high-level directive, however they want a transparent mission to keep away from drifting astray. By offering a brief define or goal description and asking the AI to provide a full specification (e.g., a spec.md), you create a persistent reference for the agent. Planning prematurely issues much more with an agent: You may iterate on the plan first, then hand it off to the agent to jot down the code. The spec turns into the primary artifact you and the AI construct collectively.

Sensible strategy: Begin a brand new coding session by prompting 

You might be an AI software program engineer. Draft an in depth specification for
[project X] overlaying goals, options, constraints, and a step-by-step plan.

Preserve your preliminary immediate high-level: e.g., “Construct an internet app the place customers can
observe duties (to-do record), with person accounts, a database, and a easy UI.”

The agent may reply with a structured draft spec: an outline, function record, tech stack strategies, information mannequin, and so forth. This spec then turns into the “supply of fact” that each you and the agent can refer again to. GitHub’s AI crew promotes spec-driven improvement the place “specs change into the shared supply of fact…dwelling, executable artifacts that evolve with the venture.” Earlier than writing any code, overview and refine the AI’s spec. Be sure it aligns along with your imaginative and prescient and proper any hallucinations or off-target particulars.

Use Plan Mode to implement planning-first: Instruments like Claude Code supply a Plan Mode that restricts the agent to read-only operations—it could analyze your codebase and create detailed plans however gained’t write any code till you’re prepared. That is superb for the planning part: Begin in Plan Mode (Shift+Tab in Claude Code), describe what you wish to construct, and let the agent draft a spec whereas exploring your present code. Ask it to make clear ambiguities by questioning you in regards to the plan. Have it overview the plan for structure, greatest practices, safety dangers, and testing technique. The purpose is to refine the plan till there’s no room for misinterpretation. Solely then do you exit Plan Mode and let the agent execute. This workflow prevents the frequent lure of leaping straight into code era earlier than the spec is stable.

Use the spec as context: As soon as accepted, save this spec (e.g., as SPEC.md) and feed related sections into the agent as wanted. Many builders utilizing a robust mannequin do precisely this. The spec file persists between periods, anchoring the AI every time work resumes on the venture. This mitigates the forgetfulness that may occur when the dialog historical past will get too lengthy or when it’s important to restart an agent. It’s akin to how one would use a product necessities doc (PRD) in a crew: a reference that everybody (human or AI) can seek the advice of to remain on observe. Skilled of us usually “write good documentation first and the mannequin could possibly construct the matching implementation from that enter alone” as one engineer noticed. The spec is that documentation.

Preserve it purpose oriented: A high-level spec for an AI agent ought to concentrate on what and why greater than the nitty-gritty how (no less than initially). Consider it just like the person story and acceptance standards: Who’s the person? What do they want? What does success appear like? (For instance, “Consumer can add, edit, full duties; information is saved persistently; the app is responsive and safe.”) This retains the AI’s detailed spec grounded in person wants and consequence, not simply technical to-dos. Because the GitHub Spec Package docs put it, present a high-level description of what you’re constructing and why, and let the coding agent generate an in depth specification specializing in person expertise and success standards. Beginning with this big-picture imaginative and prescient prevents the agent from dropping sight of the forest for the timber when it later will get into coding.

2. Construction the Spec Like a Skilled PRD (or SRS)

Deal with your AI spec as a structured doc (PRD) with clear sections, not a free pile of notes.

Many builders deal with specs for brokers very similar to conventional product requirement paperwork (PRDs) or system design docs: complete, well-organized, and simple for a “literal-minded” AI to parse. This formal strategy provides the agent a blueprint to comply with and reduces ambiguity.

The six core areas

GitHub’s evaluation of over 2,500 agent configuration information revealed a transparent sample: The simplest specs cowl six areas. Use this as a guidelines for completeness:

1. Instructions: Put executable instructions early—not simply device names however full instructions with flags: npm take a look at, pytest -v, npm run construct. The agent will reference these continuously.
2. Testing: The right way to run assessments, what framework you employ, the place take a look at information dwell, and what protection expectations exist.
3. Venture construction: The place supply code lives, the place assessments go, the place docs belong. Be express: “src/ for software code, assessments/ for unit assessments, docs/ for documentation.”
4. Code type: One actual code snippet displaying your type beats three paragraphs describing it. Embrace naming conventions, formatting guidelines, and examples of excellent output.
5. Git workflow: Department naming, commit message format, PR necessities. The agent can comply with these in the event you spell them out.
6. Boundaries: What the agent ought to by no means contact—secrets and techniques, vendor directories, manufacturing configs, particular folders. “By no means commit secrets and techniques” was the only most typical useful constraint within the GitHub research.

Be particular about your stack: Say “React 18 with TypeScript, Vite, and Tailwind CSS,” not “React venture.” Embrace variations and key dependencies. Imprecise specs produce imprecise code.

Use a constant format: Readability is king. Many devs use Markdown headings and even XML-like tags within the spec to delineate sections as a result of AI fashions deal with well-structured textual content higher than free-form prose. For instance, you may construction the spec as:

# Venture Spec: My crew's duties app


## Goal
- Construct an internet app for small groups to handle duties...


## Tech Stack
- React 18+, TypeScript, Vite, Tailwind CSS
- Node.js/Specific backend, PostgreSQL, Prisma ORM


## Instructions
- Construct: `npm run construct` (compiles TypeScript, outputs to dist/)
- Take a look at: `npm take a look at` (runs Jest, should move earlier than commits)
- Lint: `npm run lint --fix` (auto-fixes ESLint errors)


## Venture Construction
- `src/` – Utility supply code
- `assessments/` – Unit and integration assessments
- `docs/` – Documentation


## Boundaries
- ✅ At all times: Run assessments earlier than commits, comply with naming conventions
- ⚠️ Ask first: Database schema modifications, including dependencies
- 🚫 By no means: Commit secrets and techniques, edit node_modules/, modify CI config

This degree of group not solely helps you suppose clearly but in addition helps the AI discover data. Anthropic engineers suggest organizing prompts into distinct sections (like , , , and so forth.) for precisely this motive: It provides the mannequin sturdy cues about which data is which. And keep in mind, “minimal doesn’t essentially imply quick”—don’t shrink back from element within the spec if it issues, however hold it centered.

Combine specs into your toolchain: Deal with specs as “executable artifacts” tied to model management and CI/CD. The GitHub Spec Package makes use of a four-phase gated workflow that makes your specification the middle of your engineering course of. As a substitute of writing a spec and setting it apart, the spec drives the implementation, checklists, and activity breakdowns. Your main function is to steer; the coding agent does the majority of the writing. Every part has a selected job, and also you don’t transfer to the subsequent one till the present activity is totally validated:

1. Specify: You present a high-level description of what you’re constructing and why, and the coding agent generates an in depth specification. This isn’t about technical stacks or app design—it’s about person journeys, experiences, and what success seems like. Who will use this? What downside does it clear up? How will they work together with it? Consider it as mapping the person expertise you wish to create, and letting the coding agent flesh out the main points. This turns into a dwelling artifact that evolves as you study extra.

2. Plan: Now you get technical. You present your required stack, structure, and constraints, and the coding agent generates a complete technical plan. If your organization standardizes on sure applied sciences, that is the place you say so. Should you’re integrating with legacy programs or have compliance necessities, all of that goes right here. You may ask for a number of plan variations to match approaches. Should you make inner docs accessible, the agent can combine your architectural patterns immediately into the plan.

3. Duties: The coding agent takes the spec and plan and breaks them into precise work—small, reviewable chunks that every clear up a selected piece of the puzzle. Every activity needs to be one thing you possibly can implement and take a look at in isolation, virtually like test-driven improvement to your AI agent. As a substitute of “construct authentication,” you get concrete duties like “create a person registration endpoint that validates electronic mail format.”

4. Implement: Your coding agent tackles duties one after the other (or in parallel). As a substitute of reviewing thousand-line code dumps, you overview centered modifications that clear up particular issues. The agent is aware of what to construct (specification), methods to construct it (plan), and what to work on (activity). Crucially, your function is to confirm at every part: Does the spec seize what you need? Does the plan account for constraints? Are there edge instances the AI missed? The method builds in checkpoints so that you can critique, spot gaps, and course-correct earlier than shifting ahead.

This gated workflow prevents what Willison calls “home of playing cards code”: fragile AI outputs that collapse below scrutiny. Anthropic’s Abilities system gives the same sample, letting you outline reusable Markdown-based behaviors that brokers invoke. By embedding your spec in these workflows, you make sure the agent can’t proceed till the spec is validated, and modifications propagate routinely to activity breakdowns and assessments.

Contemplate brokers.md for specialised personas: For instruments like GitHub Copilot, you possibly can create brokers.md information that outline specialised agent personas—a @docs-agent for technical writing, a @test-agent for QA, a @security-agent for code overview. Every file acts as a centered spec for that persona’s conduct, instructions, and limits. That is significantly helpful whenever you need completely different brokers for various duties slightly than one general-purpose assistant.

Design for agent expertise (AX): Simply as we design APIs for developer expertise (DX), take into account designing specs for “agent expertise.” This implies clear, parseable codecs: OpenAPI schemas for any APIs the agent will eat, llms.txt information that summarize documentation for LLM consumption, and express sort definitions. The Agentic AI Basis (AAIF) is standardizing protocols like MCP (Mannequin Context Protocol) for device integration. Specs that comply with these patterns are simpler for brokers to eat and act on reliably.

PRD versus SRS mindset: It helps to borrow from established documentation practices. For AI agent specs, you’ll usually mix these into one doc (as illustrated above), however overlaying each angles serves you effectively. Writing it like a PRD ensures you embody user-centric context (“the why behind every function”) so the AI doesn’t optimize for the incorrect factor. Increasing it like an SRS ensures you nail down the specifics the AI might want to really generate appropriate code (like what database or API to make use of). Builders have discovered that this additional upfront effort pays off by drastically lowering miscommunications with the agent later.

Make the spec a “dwelling doc”: Don’t write it and overlook it. Replace the spec as you and the agent make selections or uncover new data. If the AI needed to change the info mannequin otherwise you determined to chop a function, mirror that within the spec so it stays the bottom fact. Consider it as version-controlled documentation. In spec-driven workflows, the spec drives implementation, assessments, and activity breakdowns, and also you don’t transfer to coding till the spec is validated. This behavior retains the venture coherent, particularly in the event you or the agent step away and are available again later. Bear in mind, the spec isn’t only for the AI—it helps you because the developer keep oversight and make sure the AI’s work meets the actual necessities.

3. Break Duties into Modular Prompts and Context, Not One Massive Immediate

Divide and conquer: Give the AI one centered activity at a time slightly than a monolithic immediate with every thing directly.

Skilled AI engineers have discovered that making an attempt to stuff your complete venture (all necessities, all code, all directions) right into a single immediate or agent message is a recipe for confusion. Not solely do you danger hitting token limits; you additionally danger the mannequin dropping focus because of the “curse of directions”—too many directives inflicting it to comply with none of them effectively. The answer is to design your spec and workflow in a modular manner, tackling one piece at a time and pulling in solely the context wanted for that piece.

The curse of an excessive amount of context/directions: Analysis has confirmed what many devs anecdotally noticed: as you pile on extra directions or information into the immediate, the mannequin’s efficiency in adhering to every one drops considerably. One research dubbed this the “curse of directions”, displaying that even GPT-4 and Claude wrestle when requested to fulfill many necessities concurrently. In sensible phrases, in the event you current 10 bullet factors of detailed guidelines, the AI may obey the primary few and begin overlooking others. The higher technique is iterative focus. Tips from trade counsel decomposing advanced necessities into sequential, easy directions as a greatest apply. Focus the AI on one subproblem at a time, get that accomplished, then transfer on. This retains the standard excessive and errors manageable.

Divide the spec into phases or parts: In case your spec doc may be very lengthy or covers plenty of floor, take into account splitting it into elements (both bodily separate information or clearly separate sections). For instance, you may need a piece for “backend API spec” and one other for “frontend UI spec.” You don’t must at all times feed the frontend spec to the AI when it’s engaged on the backend, and vice versa. Many devs utilizing multi-agent setups even create separate brokers or subprocesses for every half (e.g., one agent works on database/schema, one other on API logic, one other on frontend—every with the related slice of the spec). Even in the event you use a single agent, you possibly can emulate this by copying solely the related spec part into the immediate for that activity. Keep away from context overload: Don’t combine authentication duties with database schema modifications in a single go, because the DigitalOcean AI information warns. Preserve every immediate tightly scoped to the present purpose.

Prolonged TOC/summaries for big specs: One intelligent approach is to have the agent construct an prolonged desk of contents with summaries for the spec. That is basically a “spec abstract” that condenses every part into a number of key factors or key phrases, and references the place particulars could be discovered. For instance, in case your full spec has a piece on safety necessities spanning 500 phrases, you may need the agent summarize it to: “Safety: Use HTTPS, shield API keys, implement enter validation (see full spec §4.2).” By making a hierarchical abstract within the planning part, you get a chook’s-eye view that may keep within the immediate, whereas the tremendous particulars stay offloaded until wanted. This prolonged TOC acts as an index: The agent can seek the advice of it and say, “Aha, there’s a safety part I ought to take a look at,” and you may then present that part on demand. It’s much like how a human developer skims an overview after which flips to the related web page of a spec doc when engaged on a selected half.

To implement this, you possibly can immediate the agent after writing the spec: “Summarize the spec above into a really concise define with every part’s key factors and a reference tag.” The consequence could be an inventory of sections with one or two sentence summaries. That abstract could be stored within the system or assistant message to information the agent’s focus with out consuming up too many tokens. This hierarchical summarization strategy is understood to assist LLMs keep long-term context by specializing in the high-level construction. The agent carries a “psychological map” of the spec.

Make the most of subagents or “abilities” for various spec elements: One other superior strategy is utilizing a number of specialised brokers (what Anthropic calls subagents or what you may name “abilities”). Every subagent is configured for a selected space of experience and given the portion of the spec related to that space. As an illustration, you may need a database designer subagent that solely is aware of in regards to the information mannequin part of the spec, and an API coder subagent that is aware of the API endpoints spec. The primary agent (or an orchestrator) can route duties to the suitable subagent routinely.

The profit is every agent has a smaller context window to cope with and a extra centered function, which may enhance accuracy and permit parallel work on unbiased duties. Anthropic’s Claude Code helps this by letting you outline subagents with their very own system prompts and instruments. “Every subagent has a selected function and experience space, makes use of its personal context window separate from the primary dialog, and has a customized system immediate guiding its conduct,” as their docs describe. When a activity comes up that matches a subagent’s area, Claude can delegate that activity to it, with the subagent returning outcomes independently.

Parallel brokers for throughput: Working a number of brokers concurrently is rising as “the subsequent massive factor” for developer productiveness. Relatively than ready for one agent to complete earlier than beginning one other activity, you possibly can spin up parallel brokers for non-overlapping work. Willison describes this as “embracing parallel coding brokers” and notes it’s “surprisingly efficient, if mentally exhausting.” The secret is scoping duties so brokers don’t step on one another: One agent codes a function whereas one other writes assessments, or separate parts get constructed concurrently. Orchestration frameworks like LangGraph or OpenAI Swarm might help coordinate these brokers, and shared reminiscence by way of vector databases (like Chroma) lets them entry frequent context with out redundant prompting.

Single versus multi-agent: When to make use of every

In apply, utilizing subagents or skill-specific prompts may appear like: You keep a number of spec information (or immediate templates)—e.g., SPEC_backend.md, SPEC_frontend.md—and also you inform the AI, “For backend duties, seek advice from SPEC_backend; for frontend duties seek advice from SPEC_frontend.” Or in a device like Cursor/Claude, you really spin up a subagent for every. That is actually extra advanced to arrange than a single-agent loop, however it mimics what human builders do: We mentally compartmentalize a big spec into related chunks. (You don’t hold the entire 50-page spec in your head directly; you recall the half you want for the duty at hand, and have a normal sense of the general structure.) The problem, as famous, is managing interdependencies: The subagents should nonetheless coordinate. (The frontend must know the API contract from the backend spec, and so forth.) A central overview (or an “architect” agent) might help by referencing the subspecs and making certain consistency.

Focus every immediate on one activity/part: Even with out fancy multi-agent setups, you possibly can manually implement modularity. For instance, after the spec is written, your subsequent transfer could be: “Step 1: Implement the database schema.” You feed the agent the database part of the spec solely, plus any world constraints from the spec (like tech stack). The agent works on that. Then for Step 2, “Now implement the authentication function”, you present the auth part of the spec and perhaps the related elements of the schema if wanted. By refreshing the context for every main activity, you make sure the mannequin isn’t carrying plenty of stale or irrelevant data that might distract it. As one information suggests: “Begin contemporary: start new periods to clear context when switching between main options.” You may at all times remind the agent of important world guidelines (from the spec’s constraints part) every time, however don’t shove your complete spec in if it’s not all wanted.

Use in-line directives and code TODOs: One other modularity trick is to make use of your code or spec as an energetic a part of the dialog. As an illustration, scaffold your code with // TODO feedback that describe what must be accomplished, and have the agent fill them one after the other. Every TODO basically acts as a mini-spec for a small activity. This retains the AI laser centered (“implement this particular perform in accordance with this spec snippet”), and you may iterate in a good loop. It’s much like giving the AI a guidelines merchandise to finish slightly than the entire guidelines directly.

The underside line: Small, centered context beats one big immediate. This improves high quality and retains the AI from getting “overwhelmed” by an excessive amount of directly. As one set of greatest practices sums up, present “One Activity Focus” and “Related data solely” to the mannequin, and keep away from dumping every thing all over the place. By structuring the work into modules—and utilizing methods like spec summaries or subspec brokers—you’ll navigate round context measurement limits and the AI’s short-term reminiscence cap. Bear in mind, a well-fed AI is sort of a well-fed perform: Give it solely the inputs it wants for the job at hand.

4. Construct in Self-Checks, Constraints, and Human Experience

Make your spec not only a to-do record for the agent but in addition a information for high quality management—and don’t be afraid to inject your individual experience.

A superb spec for an AI agent anticipates the place the AI may go incorrect and units up guardrails. It additionally takes benefit of what you already know (area information, edge instances, “gotchas”) so the AI doesn’t function in a vacuum. Consider the spec as each coach and referee for the AI: It ought to encourage the appropriate strategy and name out fouls.

Use three-tier boundaries: GitHub’s evaluation of two,500+ agent information discovered that the simplest specs use a three-tier boundary system slightly than a easy record of don’ts. This offers the agent clearer steering on when to proceed, when to pause, and when to cease:

✅ At all times do: Actions the agent ought to take with out asking. “At all times run assessments earlier than commits.” “At all times comply with the naming conventions within the type information.” “At all times log errors to the monitoring service.”

⚠️ Ask first: Actions that require human approval. “Ask earlier than modifying database schemas.” “Ask earlier than including new dependencies.” “Ask earlier than altering CI/CD configuration.” This tier catches high-impact modifications that could be tremendous however warrant a human verify.

🚫 By no means do: Exhausting stops. “By no means commit secrets and techniques or API keys.” “By no means edit node_modules/ or vendor/.” “By no means take away a failing take a look at with out express approval.” “By no means commit secrets and techniques” was the only most typical useful constraint within the research.

This three-tier strategy is extra nuanced than a flat record of guidelines. It acknowledges that some actions are at all times secure, some want oversight, and a few are categorically off-limits. The agent can proceed confidently on “At all times” gadgets, flag “Ask first” gadgets for overview, and hard-stop on “By no means” gadgets.

Encourage self-verification: One highly effective sample is to have the agent confirm its work towards the spec routinely. In case your tooling permits, you possibly can combine checks like unit assessments or linting that the AI can run after producing code. However even on the spec/immediate degree, you possibly can instruct the AI to double-check (e.g., “After implementing, evaluate the consequence with the spec and ensure all necessities are met. Listing any spec gadgets that aren’t addressed.”). This pushes the LLM to mirror on its output relative to the spec, catching omissions. It’s a type of self-audit constructed into the method.

As an illustration, you may append to a immediate: “(After writing the perform, overview the above necessities record and guarantee every is glad, marking any lacking ones).” The mannequin will then (ideally) output the code adopted by a brief guidelines indicating if it met every requirement. This reduces the prospect it forgets one thing earlier than you even run assessments. It’s not foolproof, however it helps.

LLM-as-a-Choose for subjective checks: For standards which can be arduous to check routinely—code type, readability, adherence to architectural patterns—think about using “LLM-as-a-Choose.” This implies having a second agent (or a separate immediate) overview the primary agent’s output towards your spec’s high quality pointers. Anthropic and others have discovered this efficient for subjective analysis. You may immediate “Evaluation this code for adherence to our type information. Flag any violations.” The choose agent returns suggestions that both will get included or triggers a revision. This provides a layer of semantic analysis past syntax checks.

Conformance testing: Willison advocates constructing conformance suites—language-independent assessments (usually YAML primarily based) that any implementation should move. These act as a contract: Should you’re constructing an API, the conformance suite specifies anticipated inputs/outputs, and the agent’s code should fulfill all instances. That is extra rigorous than advert hoc unit assessments as a result of it’s derived immediately from the spec and could be reused throughout implementations. Embrace conformance standards in your spec’s success part (e.g., “Should move all instances in conformance/api-tests.yaml”).

Leverage testing within the spec: If attainable, incorporate a take a look at plan and even precise assessments in your spec and immediate circulate. In conventional improvement, we use TDD or write take a look at instances to make clear necessities—you are able to do the identical with AI. For instance, within the spec’s success standards, you may say, “These pattern inputs ought to produce these outputs…” or “The next unit assessments ought to move.” The agent could be prompted to run by way of these instances in its head or really execute them if it has that functionality. Willison famous that having a sturdy take a look at suite is like giving the brokers superpowers: They’ll validate and iterate shortly when assessments fail. In an AI coding context, writing a little bit of pseudocode for assessments or anticipated outcomes within the spec can information the agent’s implementation. Moreover, you should utilize a devoted “take a look at agent” in a subagent setup that takes the spec’s standards and repeatedly verifies the “code agent’s” output.

Convey your area information: Your spec ought to mirror insights that solely an skilled developer or somebody with context would know. For instance, in the event you’re constructing an ecommerce agent and you already know that “merchandise” and “classes” have a many-to-many relationship, state that clearly. (Don’t assume the AI will infer it—it may not.) If a sure library is notoriously tough, point out pitfalls to keep away from. Primarily, pour your mentorship into the spec. The spec can include recommendation like “If utilizing library X, be careful for reminiscence leak subject in model Y (apply workaround Z).” This degree of element is what turns a median AI output into a very sturdy answer, since you’ve steered the AI away from frequent traps.

Additionally, you probably have preferences or type pointers (say, “use purposeful parts over class parts in React”), encode that within the spec. The AI will then emulate your type. Many engineers even embody small examples within the spec (as an illustration, “All API responses needs to be JSON, e.g., {“error”: “message”} for errors.”). By giving a fast instance, you anchor the AI to the precise format you need.

Minimalism for easy duties: Whereas we advocate thorough specs, a part of experience is realizing when to maintain it easy. For comparatively easy, remoted duties, an overbearing spec can really confuse greater than assist. Should you’re asking the agent to do one thing simple (like “heart a div on the web page”), you may simply say, “Be sure to maintain the answer concise and don’t add extraneous markup or types.” No want for a full PRD there. Conversely, for advanced duties (like “implement an OAuth circulate with token refresh and error dealing with”), that’s whenever you escape the detailed spec. A superb rule of thumb: Modify spec element to activity complexity. Don’t underspec a tough downside (the agent will flail or go off-track), however don’t overspec a trivial one (the agent may get tangled or deplete context on pointless directions).

Preserve the AI’s “persona” if wanted: Generally, a part of your spec is defining how the agent ought to behave or reply, particularly if the agent interacts with customers. For instance, if constructing a buyer assist agent, your spec may embody pointers like “Use a pleasant {and professional} tone” and “Should you don’t know the reply, ask for clarification or supply to comply with up slightly than guessing.” These sorts of guidelines (usually included in system prompts) assist hold the AI’s outputs aligned with expectations. They’re basically spec gadgets for AI conduct. Preserve them constant and remind the mannequin of them if wanted in lengthy periods. (LLMs can “drift” in type over time if not stored on a leash.)

You stay the exec within the loop: The spec empowers the agent, however you stay the last word high quality filter. If the agent produces one thing that technically meets the spec however doesn’t really feel proper, belief your judgement. Both refine the spec or immediately regulate the output. The wonderful thing about AI brokers is that they don’t get offended—in the event that they ship a design that’s off, you possibly can say, “Truly, that’s not what I meant, let’s make clear the spec and redo it.” The spec is a dwelling artifact in collaboration with the AI, not a one-time contract you possibly can’t change.

Simon Willison humorously likened working with AI brokers to “a really bizarre type of administration” and even “getting good outcomes out of a coding agent feels uncomfortably near managing a human intern.” You want to present clear directions (the spec), guarantee they’ve the required context (the spec and related information), and provides actionable suggestions. The spec units the stage, however monitoring and suggestions throughout execution are key. If an AI was a “bizarre digital intern who will completely cheat in the event you give them an opportunity,” the spec and constraints you write are the way you stop that dishonest and hold them on activity.

Right here’s the payoff: A superb spec doesn’t simply inform the AI what to construct; it additionally helps it self-correct and keep inside secure boundaries. By baking in verification steps, constraints, and your hard-earned information, you drastically enhance the chances that the agent’s output is appropriate on the primary attempt (or no less than a lot nearer to appropriate). This reduces iterations and people “Why on Earth did it do this?” moments.

5. Take a look at, Iterate, and Evolve the Spec (and Use the Proper Instruments)

Consider spec writing and agent constructing as an iterative loop: take a look at early, collect suggestions, refine the spec, and leverage instruments to automate checks.

The preliminary spec shouldn’t be the top—it’s the start of a cycle. One of the best outcomes come whenever you regularly confirm the agent’s work towards the spec and regulate accordingly. Additionally, trendy AI devs use numerous instruments to assist this course of (from CI pipelines to context administration utilities).

Steady testing: Don’t wait till the top to see if the agent met the spec. After every main milestone and even every perform, run assessments or no less than do fast handbook checks. If one thing fails, replace the spec or immediate earlier than continuing. For instance, if the spec stated, “Passwords have to be hashed with bcrypt” and also you see the agent’s code storing plain textual content, cease and proper it (and remind the spec or immediate in regards to the rule). Automated assessments shine right here: Should you offered assessments (or write them as you go), let the agent run them. In lots of coding agent setups, you possibly can have an agent run npm take a look at or related after ending a activity. The outcomes (failures) can then feed again into the subsequent immediate, successfully telling the agent “Your output didn’t meet spec on X, Y, Z—repair it.” This sort of agentic loop (code > take a look at > repair > repeat) is extraordinarily highly effective and is how instruments like Claude Code or Copilot Labs are evolving to deal with bigger duties. At all times outline what “accomplished” means (by way of assessments or standards) and verify for it.

Iterate on the spec itself: Should you uncover that the spec was incomplete or unclear (perhaps the agent misunderstood one thing otherwise you realized you missed a requirement), replace the spec doc. Then explicitly resync the agent with the brand new spec: “I’ve up to date the spec as follows… Given the up to date spec, regulate the plan or refactor the code accordingly.” This fashion the spec stays the only supply of fact. It’s much like how we deal with altering necessities in regular dev, however on this case you’re additionally the product supervisor to your AI agent. Preserve model historical past if attainable (even simply by way of commit messages or notes), so you already know what modified and why.

Make the most of context administration and reminiscence instruments: There’s a rising ecosystem of instruments to assist handle AI agent context and information. As an illustration, retrieval-augmented era (RAG) is a sample the place the agent can pull in related chunks of knowledge from a information base (like a vector database) on the fly. In case your spec is large, you would embed sections of it and let the agent retrieve essentially the most related elements when wanted, as a substitute of at all times offering the entire thing. There are additionally frameworks implementing the Mannequin Context Protocol (MCP), which automates feeding the appropriate context to the mannequin primarily based on the present activity. One instance is Context7 (context7.com), which may auto-fetch related context snippets from docs primarily based on what you’re engaged on. In apply, this may imply the agent notices you’re engaged on “cost processing” and it pulls the funds part of your spec or documentation into the immediate. Contemplate leveraging such instruments or organising a rudimentary model (even a easy search in your spec doc).

Parallelize rigorously: Some builders run a number of agent situations in parallel on completely different duties (as talked about earlier with subagents). This may velocity up improvement (e.g., one agent generates code whereas one other concurrently writes assessments, or two options are constructed concurrently). Should you go this route, make sure the duties are actually unbiased or clearly separated to keep away from conflicts. (The spec ought to be aware any dependencies.) For instance, don’t have two brokers writing to the identical file directly. One workflow is to have an agent generate code and one other overview it in parallel, or to have separate parts constructed that combine later. That is superior utilization and could be mentally taxing to handle. (As Willison admitted, working a number of brokers is surprisingly efficient, if mentally exhausting!) Begin with at most 2–3 brokers to maintain issues manageable.

Model management and spec locks: Use Git or your model management of alternative to trace what the agent does. Good model management habits matter much more with AI help. Commit the spec file itself to the repo. This not solely preserves historical past, however the agent may even use git diff or blame to know modifications. (LLMs are fairly able to studying diffs.) Some superior agent setups let the agent question the VCS historical past to see when one thing was launched—surprisingly, fashions could be “fiercely competent at Git.” By conserving your spec within the repo, you permit each you and the AI to trace evolution. There are instruments (like GitHub Spec Package talked about earlier) that combine spec-driven improvement into the Git workflow—as an illustration, gating merges on up to date specs or producing checklists from spec gadgets. Whilst you don’t want these instruments to succeed, the takeaway is to deal with the spec like code: Preserve it diligently.

Price and velocity issues: Working with giant fashions and lengthy contexts could be gradual and costly. A sensible tip is to make use of mannequin choice and batching well. Maybe use a less expensive/quicker mannequin for preliminary drafts or repetitions, and reserve essentially the most succesful (and costly) mannequin for remaining outputs or advanced reasoning. Some builders use GPT-4 or Claude for planning and significant steps, however offload less complicated expansions or refactors to an area mannequin or a smaller API mannequin. If utilizing a number of brokers, perhaps not all have to be high tier; a test-running agent or a linter agent might be a smaller mannequin. Additionally take into account throttling context measurement: Don’t feed 20K tokens if 5K will do. As we mentioned, extra tokens can imply diminishing returns.

Monitor and log every thing: In advanced agent workflows, logging the agent’s actions and outputs is important. Verify the logs to see if the agent is deviating or encountering errors. Many frameworks present hint logs or permit printing the agent’s chain of thought (particularly in the event you immediate it to suppose step-by-step). Reviewing these logs can spotlight the place the spec or directions may need been misinterpreted. It’s not in contrast to debugging a program—besides the “program” is the dialog/immediate chain. If one thing bizarre occurs, return to the spec/directions to see if there was ambiguity.

Study and enhance: Lastly, deal with every venture as a studying alternative to refine your spec-writing ability. Possibly you’ll uncover {that a} sure phrasing persistently confuses the AI, or that organizing spec sections in a sure manner yields higher adherence. Incorporate these classes into the subsequent spec. The sphere of AI brokers is quickly evolving, so new greatest practices (and instruments) emerge continuously. Keep up to date by way of blogs (like those by Simon Willison, Andrej Karpathy, and so forth.), and don’t hesitate to experiment.

A spec for an AI agent isn’t “write as soon as, accomplished.” It’s a part of a steady cycle of instructing, verifying, and refining. The payoff for this diligence is substantial: By catching points early and conserving the agent aligned, you keep away from expensive rewrites or failures later. As one AI engineer quipped, utilizing these practices can really feel like having “a military of interns” working for you, however it’s important to handle them effectively. A superb spec, repeatedly maintained, is your administration device.

Keep away from Frequent Pitfalls

Earlier than wrapping up, it’s value calling out antipatterns that may derail even well-intentioned spec-driven workflows. The GitHub research of two,500+ agent information revealed a stark divide: “Most agent information fail as a result of they’re too imprecise.” Listed here are the errors to keep away from:

Imprecise prompts: “Construct me one thing cool” or “Make it work higher” provides the agent nothing to anchor on. As Baptiste Studer places it: “Imprecise prompts imply incorrect outcomes.” Be particular about inputs, outputs, and constraints. “You’re a useful coding assistant” doesn’t work. “You’re a take a look at engineer who writes assessments for React parts, follows these examples, and by no means modifies supply code” does.

Overlong contexts with out summarization: Dumping 50 pages of documentation right into a immediate and hoping the mannequin figures it out not often works. Use hierarchical summaries (as mentioned in precept 3) or RAG to floor solely what’s related. Context size shouldn’t be an alternative to context high quality.

Skipping human overview: Willison has a private rule—“I gained’t commit code I couldn’t clarify to another person.” Simply because the agent produced one thing that passes assessments doesn’t imply it’s appropriate, safe, or maintainable. At all times overview important code paths. The “home of playing cards” metaphor applies: AI-generated code can look stable however collapse below edge instances you didn’t take a look at.

Conflating vibe coding with manufacturing engineering: Speedy prototyping with AI (“vibe coding”) is nice for exploration and throwaway tasks. However delivery that code to manufacturing with out rigorous specs, assessments, and overview is asking for bother. I distinguish “vibe coding” from “AI-assisted engineering”—the latter requires the self-discipline this information describes. Know which mode you’re in.

Ignoring the “deadly trifecta”: Willison warns of three properties that make AI brokers harmful: velocity (they work quicker than you possibly can overview), nondeterminism (identical enter, completely different outputs), and price (encouraging nook chopping on verification). Your spec and overview course of should account for all three. Don’t let velocity outpace your skill to confirm.

Lacking the six core areas: In case your spec doesn’t cowl instructions, testing, venture construction, code type, git workflow, and limits, you’re possible lacking one thing the agent wants. Use the six-area guidelines from part 2 as a sanity verify earlier than handing off to the agent.

Conclusion

Writing an efficient spec for AI coding brokers requires stable software program engineering ideas mixed with adaptation to LLM quirks. Begin with readability of function and let the AI assist develop the plan. Construction the spec like a severe design doc, overlaying the six core areas and integrating it into your toolchain so it turns into an executable artifact, not simply prose. Preserve the agent’s focus tight by feeding it one piece of the puzzle at a time (and take into account intelligent ways like abstract TOCs, subagents, or parallel orchestration to deal with massive specs). Anticipate pitfalls by together with three-tier boundaries (at all times/ask first/by no means), self-checks, and conformance assessments—basically, educate the AI methods to not fail. And deal with the entire course of as iterative: use assessments and suggestions to refine each the spec and the code repeatedly.

Comply with these pointers and your AI agent shall be far much less prone to “break down” below giant contexts or wander away into nonsense.

Completely satisfied spec-writing!