Explore a topic
Working with AI
Give AI a clear task and context. Check its work and set limits on what it can do.
Start with a practical guide
Worked Case: Check a Node.js Assertion Before You Use It
A concrete verification loop for an AI suggestion that names a software package, API or dependency with confident but unverified details.
Read the story LongreadDebug an intermittent failure
Investigate a bug that appears only sometimes or a flaky test. Keep failed and successful runs, compare what changed and test competing explanations. Record what remains unknown.
Read the story LongreadCheck an AI Answer Before You Act
Before acting on an AI answer, identify the claim that could change your decision. Check it against a source outside the AI, test the result, and pause if an important fact remains unknown.
Read the storyStart with a collection
Compare all collections on this topic
Use AI where it helps, and keep the thinking that still matters
Turn recent human-AI research into practical rules for task fit, verification effort, decision ownership, learning retention and measurement of real work gains.
Let coding agents move fast inside a reviewable security boundary
Turn AI-assisted coding into an inspectable software-development workflow with bounded repository scope, untrusted-context handling, dependency checks, independent tests, protected build/CI surfaces, secret controls, egress limits and accountable human merge ownership.
Operate AI agents as systems you can replay, verify and constrain
Add practical 2026 agent-engineering techniques for replay, evaluation, tool routing, computer use, scoped authorization and deterministic execution without turning conference claims into universal guarantees.
Let AI do useful work without giving it accidental authority
Design AI-assisted workflows so tools, permissions, evidence, approvals, testing and monitoring match the real task and limit the blast radius of a bad output.
Calibrate when to rely on AI instead of measuring trust as a feeling
Use recent 2025–2026 human-AI research to separate confidence, accuracy, metacognitive sensitivity and actual advice adoption so reliance can be tested rather than assumed.
Make AI-assisted work earn your trust
Separate demonstrations from evaluations and make errors, evidence gaps and action authority inspectable before delegating consequential work.
Make AI work improve from failures instead of accumulating rituals
Use eval-driven development, durable guardrails, clean experiments and reusable research or automation artifacts so everyday AI workflows learn from repeated work rather than restarting from chat every time.
Give AI the right context, memory and reusable skills
Use modern context engineering, durable memory and evaluated skills to make repeated AI work more reliable without stuffing every fact and instruction into every conversation.
Make coding agents work in inspectable increments
Turn current long-horizon coding-agent practice into concrete feature ledgers, cold-start checks, evaluator criteria and safe parallel work that a human can steer without micromanaging every line.
Make the agent loop finish, recover and stay inspectable
Turn current 2025-2026 agent engineering into practical controls for bounded loops, context, memory, checkpointing, evaluation and trajectory monitoring.
133 ideas
Bound every autonomous agent loop before it starts
A loop without a hard edge is an outage waiting for a goal condition to fail.
Read the idea ProtocolWrite the completion condition before the agent starts iterating
An agent loop cannot finish reliably if 'done' exists only in the model's mood.
Read the idea ProtocolDetect stagnation separately from completion
More motion is not the same thing as more progress.
Read the idea HeuristicTreat repeated state-action pairs as a loop alarm
If the state did not change, the same action is usually a retry—not a new strategy.
Read the idea PrincipleRetry after a state change; replan after the same failure
A retry is justified by changed conditions; otherwise it is often just repetition.
Read the idea ProtocolCheckpoint meaningful progress before a long agent crosses a fragile boundary
Progress that exists only in the current context window is not durable progress.
Read the idea PrincipleStore durable task state outside the context window
Context is working memory, not a durable project database.
Read the idea ProtocolCompact context by preserving decisions and unresolved work—not every tool result
Compaction should save the project, not the transcript.
Read the idea PrincipleRetrieve context just in time instead of preloading the whole project
Relevant context is valuable; irrelevant context taxes every token after it.
Read the idea ProtocolLet subagents write durable artifacts instead of relaying everything through the coordinator
Every relay is another chance to lose detail.
Read the idea ProtocolEvaluate the same agent task across multiple trials
A nondeterministic system needs more than one audition.
Read the idea ProtocolRead eval transcripts before trusting the score
A score can fail because the agent failed—or because the eval did.
Read the idea ProtocolCombine grader types instead of asking one LLM judge to decide everything
A flexible judge is useful; a monoculture of judgment is fragile.
Read the idea ChecklistTrack tool errors, tool calls, runtime and tokens as agent diagnostics
The path to the answer reveals inefficiency before users notice the bill or latency.
Read the idea ProtocolMonitor the whole agent trajectory, not only individual allowed actions
A safe-looking step can participate in an unsafe-looking trajectory.
Read the idea ChecklistGive the agent only the tools this job needs
Every extra tool is another verb the system can accidentally conjugate.
Read the idea PrincipleStart an agent read-only when writing is not required
Reading first gives you evidence. Writing first gives you evidence plus cleanup.
Read the idea PrinciplePrefer a task-shaped tool to an open-ended one
A function named `create_invoice_draft` has fewer dangerous interpretations than `run_anything`.
Read the idea PrincipleRun agent actions in the user's authorization context
A helpful assistant should not quietly become a shared administrator.
Read the idea ProtocolPut approval immediately before the high-impact action
Approval at the start of a long plan is not approval of the action the plan eventually invented.
Read the idea PrincipleTreat retrieved content as data, not as new authority
The page you asked the agent to read should not get to rewrite the job description.
Read the idea ChecklistKeep secrets out of the system prompt
A prompt is a poor vault, even when nobody intends to show it.
Read the idea PrincipleEnforce permissions outside the model
A sentence in a prompt is guidance. An authorization check is a control.
Read the idea ProtocolValidate model output for the system that will consume it
Readable text becomes a different risk when the next component treats it as code.
Read the ideaExplore another topic
Critical thinking and evidence
Test claims, separate evidence from interpretation and ask questions that can change what you believe.
70 ideasProject delivery
Estimate the work, agree on what counts as finished and check risky changes before you make them.
96 ideasKnowledge management and research
Find information, check its sources and keep useful notes easy to find and update.
63 ideas