The next is Half 3 of three from Addy Osmani’s unique publish “Context Engineering: Bringing Engineering Self-discipline to Components.” Half 1 may be discovered right here and Half 2 right here.
Context engineering is essential, nevertheless it’s only one part of a bigger stack wanted to construct full-fledged LLM purposes—alongside issues like management circulation, mannequin orchestration, device integration, and guardrails.
In Andrej Karpathy’s phrases, context engineering is “one small piece of an rising thick layer of non-trivial software program” that powers actual LLM apps. So whereas we’ve targeted on easy methods to craft good context, it’s essential to see the place that matches within the general structure.
A production-grade LLM system sometimes has to deal with many issues past simply prompting. For instance:
- Downside decomposition and management circulation: As an alternative of treating a person question as one monolithic immediate, strong techniques usually break the issue down into subtasks or multistep workflows. As an example, an AI agent may first be prompted to stipulate a plan, then in subsequent steps be prompted to execute every step. Designing this circulation (which prompts to name in what order; easy methods to resolve branching or looping) is a traditional programming process—besides the “capabilities” are LLM calls with context. Context engineering suits right here by ensuring every step’s immediate has the information it wants, however the choice to have steps in any respect is a higher-level design. Because of this you see frameworks the place you basically write a script that coordinates a number of LLM calls and power makes use of.
- Mannequin choice and routing: You may use completely different AI fashions for various jobs. Maybe a light-weight mannequin for easy duties or preliminary solutions, and a heavyweight mannequin for closing options. Or a code-specialized mannequin for coding duties versus a common mannequin for conversational duties. The system wants logic to route requests to the suitable mannequin. Every mannequin may need completely different context size limits or formatting necessities, which the context engineering should account for (e.g., truncating context extra aggressively for a smaller mannequin). This facet is extra engineering than prompting: consider it as matching the device to the job.
- Software integrations and exterior actions: In case your AI can carry out actions (like calling an API, database queries, opening an online web page, working code), your software program must handle these capabilities. That features offering the AI with an inventory of obtainable instruments and directions on utilization, in addition to really executing these device calls and capturing the outcomes. As we mentioned, the outcomes then turn into new context for additional mannequin calls. Architecturally, this implies your app usually has a loop: immediate mannequin → if mannequin output signifies a device to make use of → execute device → incorporate consequence → immediate mannequin once more. Designing that loop reliably is a problem.
- Person interplay and UX flows: Many LLM purposes contain the person within the loop. For instance, a coding assistant may suggest modifications after which ask the person to verify making use of them. Or a writing assistant may supply a couple of draft choices for the person to choose from. These UX selections have an effect on context too. If the person says “Choice 2 seems good however shorten it,” you should carry that suggestions into the subsequent immediate (e.g., “The person selected draft 2 and requested to shorten it.”). Designing a easy human-AI interplay circulation is a part of the app, although circuitously about prompts. Nonetheless, context engineering helps it by making certain every flip’s immediate precisely displays the state of the interplay (like remembering which possibility was chosen or what the person edited manually).
- Guardrails and security: In manufacturing, it’s important to take into account misuse and errors. This may embrace content material filters (to stop poisonous or delicate outputs), authentication and permission checks for instruments (so the AI doesn’t, say, delete a database as a result of it was within the directions), and validation of outputs. Some setups use a second mannequin or guidelines to double-check the primary mannequin’s output. For instance, after the primary mannequin generates a solution, you may run one other verify: “Does this reply comprise any delicate information? If that’s the case, redact it.” These checks themselves may be carried out as prompts or as code. In both case, they usually add further directions into the context (a system message like “If the person asks for disallowed content material, refuse,” is a part of many deployed prompts). So the context may at all times embrace some security boilerplate. Balancing that (making certain the mannequin follows coverage with out compromising helpfulness) is one more piece of the puzzle.
- Analysis and monitoring: Suffice to say, you should consistently monitor how the AI is performing. Logging each request and response (with person consent and privateness in thoughts) means that you can analyze failures and outliers. You may incorporate real-time evals—e.g., scoring the mannequin’s solutions on sure standards, and if the rating is low, robotically having the mannequin attempt once more or path to a human fallback. Whereas analysis isn’t a part of producing a single immediate’s content material, it feeds again into bettering prompts and context methods over time. Primarily, you deal with the immediate and context meeting as one thing that may be debugged and optimized utilizing knowledge from manufacturing.
We’re actually speaking about a brand new type of software structure. It’s one the place the core logic includes managing data (context) and adapting it by means of a collection of AI interactions, slightly than simply working deterministic capabilities. Karpathy listed components like management flows, mannequin dispatch, reminiscence administration, device use, verification steps, and many others., on high of context filling. All collectively, they type what he jokingly calls “an rising thick layer” for AI apps—thick as a result of it’s doing rather a lot! Once we construct these techniques, we’re basically writing metaprograms: applications that choreograph one other “program” (the AI’s output) to unravel a process.
For us software program engineers, that is each thrilling and difficult. It’s thrilling as a result of it opens capabilities we didn’t have—e.g., constructing an assistant that may deal with pure language, code, and exterior actions seamlessly. It’s difficult as a result of lots of the methods are new and nonetheless in flux. We now have to consider issues like immediate versioning, AI reliability, and moral output filtering, which weren’t customary elements of app improvement earlier than. On this context, context engineering lies on the coronary heart of the system: In the event you can’t get the suitable data into the mannequin on the proper time, nothing else will save your app. However as we see, even excellent context alone isn’t sufficient; you want all of the supporting construction round it.
The takeaway is that we’re transferring from immediate design to system design. Context engineering is a core a part of that system design, nevertheless it lives alongside many different elements.
Conclusion
Key takeaway: By mastering the meeting of full context (and coupling it with strong testing), we will improve the probabilities of getting the perfect output from AI fashions.
For knowledgeable engineers, a lot of this paradigm is acquainted at its core—it’s about good software program practices—however utilized in a brand new area. Give it some thought:
- We at all times knew rubbish in, rubbish out. Now that precept manifests as “unhealthy context in, unhealthy reply out.” So we put extra work into making certain high quality enter (context) slightly than hoping the mannequin will determine it out.
- We worth modularity and abstraction in code. Now we’re successfully abstracting duties to a excessive degree (describe the duty, give examples, let AI implement) and constructing modular pipelines of AI + instruments. We’re orchestrating elements (some deterministic, some AI) slightly than writing all logic ourselves.
- We follow testing and iteration in conventional dev. Now we’re making use of the identical rigor to AI behaviors, writing evals and refining prompts as one would refine code after profiling.
In embracing context engineering, you’re basically saying, “I, the developer, am chargeable for what the AI does.” It’s not a mysterious oracle; it’s a part I must configure and drive with the suitable knowledge and guidelines.
This mindset shift is empowering. It means we don’t need to deal with the AI as unpredictable magic—we will tame it with strong engineering methods (plus a little bit of inventive immediate artistry).
Virtually, how are you going to undertake this context-centric strategy in your work?
- Spend money on knowledge and information pipelines. An enormous a part of context engineering is having the info to inject. So construct that vector search index of your documentation, or arrange that database question that your agent can use. Deal with information sources as core options in improvement. For instance, in case your AI assistant is for coding, be sure it may well pull in code from the repo or reference the model information. A number of the worth you’ll get from an AI comes from the exterior information you provide to it.
- Develop immediate templates and libraries. Slightly than advert hoc prompts, begin creating structured templates on your wants. You may need a template for “reply with quotation” or “generate code diff given error.” These turn into like capabilities you reuse. Preserve them in model management. Doc their anticipated habits. That is the way you construct up a toolkit of confirmed context setups. Over time, your workforce can share and iterate on these, simply as they might on shared code libraries.
- Use instruments and frameworks that provide you with management. Keep away from “simply give us a immediate, we do the remainder” options in case you want reliability. Go for frameworks that allow you to peek beneath the hood and tweak issues—whether or not that’s a lower-level library like LangChain or a customized orchestration you construct. The extra visibility and management you could have over context meeting, the simpler debugging will probably be when one thing goes flawed.
- Monitor and instrument every thing. In manufacturing, log the inputs and outputs (inside privateness limits) so you’ll be able to later analyze them. Use observability instruments (like LangSmith, and many others.) to hint how context was constructed for every request. When an output is unhealthy, hint again and see what the mannequin noticed—was one thing lacking? Was one thing formatted poorly? This can information your fixes. Primarily, deal with your AI system as a considerably unpredictable service that you should monitor like some other—dashboards for immediate utilization, success charges, and many others.
- Preserve the person within the loop. Context engineering isn’t nearly machine-machine information; it’s in the end about fixing a person’s drawback. Typically, the person can present context if requested the suitable method. Take into consideration UX designs the place the AI asks clarifying questions or the place the person can present additional particulars to refine the context (like attaching a file, or deciding on which codebase part is related). The time period “AI-assisted” goes each methods—AI assists the person, however the person can help AI by supplying context. A well-designed system facilitates that. For instance, if an AI reply is flawed, let the person appropriate it and feed that correction again into context for subsequent time.
- Practice your workforce (and your self). Make context engineering a shared self-discipline. In code opinions, begin reviewing prompts and context logic too. (“Is that this retrieval grabbing the suitable docs? Is that this immediate part clear and unambiguous?”) In the event you’re a tech lead, encourage workforce members to floor points with AI outputs and brainstorm how tweaking context may repair it. Data sharing is vital as a result of the sphere is new—a intelligent immediate trick or formatting perception one particular person discovers can doubtless profit others. I’ve personally realized a ton simply studying others’ immediate examples and postmortems of AI failures.
As we transfer ahead, I anticipate context engineering to turn into second nature—very like writing an API name or a SQL question is at present. It is going to be a part of the usual repertoire of software program improvement. Already, many people don’t suppose twice about doing a fast vector similarity search to seize context for a query; it’s simply a part of the circulation. In a couple of years, “Have you ever arrange the context correctly?” will probably be as frequent a code evaluation query as “Have you ever dealt with that API response correctly?”
In embracing this new paradigm, we don’t abandon the previous engineering rules—we reapply them in new methods. In the event you’ve spent years honing your software program craft, that have is extremely invaluable now: It’s what means that you can design wise flows, spot edge circumstances, and guarantee correctness. AI hasn’t made these abilities out of date; it’s amplified their significance in guiding AI. The position of the software program engineer just isn’t diminishing—it’s evolving. We’re changing into administrators and editors of AI, not simply writers of code. And context engineering is the approach by which we direct the AI successfully.
Begin pondering when it comes to what data you present to the mannequin, not simply what query you ask. Experiment with it, iterate on it, and share your findings. By doing so, you’ll not solely get higher outcomes from at present’s AI but in addition be making ready your self for the much more highly effective AI techniques on the horizon. Those that perceive easy methods to feed the AI will at all times have the benefit.
Blissful context-coding!
I’m excited to share that I’ve written a brand new AI-assisted engineering ebook with O’Reilly. In the event you’ve loved my writing right here chances are you’ll be fascinated with checking it out.
AI instruments are rapidly transferring past chat UX to stylish agent interactions. Our upcoming AI Codecon occasion, Coding for the Agentic World, will spotlight how builders are already utilizing brokers to construct modern and efficient AI-powered experiences. We hope you’ll be part of us on September 9 to discover the instruments, workflows, and architectures defining the subsequent period of programming. It’s free to attend. Register now to save lots of your seat.
