Build with agents.
Keep your judgment.
Practical reference for building, reviewing and teaching with agents. Find the reasoning, the tradeoffs and the exact text.
Reference library
27 references
-
5 Monkeys QA swarm playbook
Web developers already trust tests for known requirements, but fast-moving UI work also needs cheap exploratory passes that click through real app state. This technique gives local agents a practical browser-facing QA job: find weird UX and state bugs before users do.
-
A trustworthy software factory loop — discussion and evidence
Detailed companion accounts of concepts, questions, demonstrations, exercises, and unresolved observations.
-
Advanced consult, image, and video contracts
Transferable contracts from the published Oracle resource family: premise coverage, bounded escalation, attachment proof, multimodal continuity, and honest completion.
-
Agent Markers debugging workflows: practical reference
Browser-debugging reference covering the agent-markers setup prompt, perspective-based exploratory QA, bounded event capture and marker schemas, browser/global APIs, privacy and cleanup, JSON and test-artifact exports, replay capsules, app-specific…
-
Agent Markers debugging workflows: practice drills
Exercises for marking browser failures, initializing Agent Markers, exporting bounded evidence, reviewing privacy, attaching exports to tests, verifying projects, writing debug prompts, designing replay capsules and app-specific shortcuts, recovering from…
-
Artifact evidence is not the same as success
Separate observed creation, command execution, visible output, and verified completion; preserve failures and the exact next check.
-
Browser Proof Field Guide
Make Codex prove rendered web behavior with routes, actions, logs, screenshots, and receipts.
-
Explore software through perspectives and runtime QA
Use perspective-based prompting and discardable QA files for non-obvious user paths; Apply the 5 Monkeys technique and use CMUX state for context-aware shortcuts; Extract implementation intent from narrated screen recordings into Gemini.
-
Fusion council decisions and evidence: practical reference
Local multi-model council reference covering skill and CLI setup, provider diversity and preflight, durable prompts, dry runs, terminal-state and artifact checks, degraded-provider recovery, privacy, and reconciliation with repo evidence before…
-
Fusion council decisions and evidence: practice drills
Exercises for deciding when a model council helps, framing bounded decisions, invoking Fusion, validating providers and completion artifacts, reconciling disagreement, handling failures, and defining a verified first implementation slice.
-
Human testimony joined to runtime evidence
Capture the moment of surprise with a bounded redacted trail and discriminate between hypotheses before changing code.
-
Human testimony joined to runtime evidence — prompts and exercises
Complete reusable prompts, setup recipes, success checks, and caveats for human testimony joined to runtime evidence.
Browse 15 more references
-
Human testimony joined to runtime evidence — questions and tradeoffs
Detailed questions and tradeoffs with concrete prompts, observable outcomes, and the limits of the example.
-
Human testimony joined to runtime evidence — worked example
Detailed worked example with concrete prompts, observable outcomes, and the limits of the example.
-
Independent reasoning and video evidence
Escalate consequential decisions with filtered context and use probes, sentinels, and bounded video analysis.
-
Independent reasoning and video evidence — discussion and evidence
Detailed companion accounts of concepts, questions, demonstrations, exercises, and unresolved observations.
-
Independent reasoning and video evidence — prompts and exercises
Complete reusable prompts, setup recipes, success checks, and caveats for independent reasoning and video evidence.
-
Independent reasoning and video evidence — questions and tradeoffs
Detailed questions and tradeoffs with concrete prompts, observable outcomes, and the limits of the example.
-
Independent reasoning and video evidence — reference patterns
Extended explanations, comparisons, experiments, and practical actions for the same operating pattern.
-
Independent reasoning and video evidence — worked example
Detailed worked example with concrete prompts, observable outcomes, and the limits of the example.
-
Make the repository agent-ready
A background workflow is only useful when the agent can prove what it changed. Start by giving the repo a verification loop. Then move repeated, narrow jobs into tiny tool-shaped agents that carry only the context they need.
-
Mark the debug moment before handoff
Logs show what happened. A marker says which moment mattered.
-
Review generated UI before building
A generated mockup is useful when it gives you something concrete to inspect. Do not jump from one polished image to implementation. Keep the source visual, choose a controlled style direction, generate against that direction, review the result, then hand…
-
Self-improving log-gated fix loop playbook
Web developers already run local dev servers, browser checks, test scripts, and agent panes; this technique turns those runtime artifacts into proof instead of vibes. It matters because UI bugs, auth regressions, and hook failures are often only obvious in logs, browser state, or terminal output, not in the agent's final message.
-
Use a model council for hard decisions
A single model can give a clean answer and still miss the important edge. Use a model council when the cost of a missed perspective is higher than the cost of waiting.
-
Verify fixes with deterministic evidence and narrow boundaries
Extract terminal pane text in CMUX as machine-readable context; Build self-improvement error loops behind log-based deterministic gates; Define natural-language contract boundaries and prune context.
-
Video analysis recipes, prompts, and evidence gates
Complete media-normalization commands, long/short analysis branches, omission and reconciliation prompts, keyframe procedures, and publication evidence gates.
No references match yet.
Try fewer words or choose another subject.