Topic tag
verification
24 guides in the catalogue cover this topic.
- Nº 008 Automate the step that slows you down Agents & Automation · Broad
Automating the bottleneck means finding the constraint that sets your pace and pointing Claude at it: four working rules distilled from Anthropic's own engineers.
- Nº 016 Guardrails for hours-long agent runs Prompting & Context · Deep
Guardrails are the support structure that keeps an hours-long agent run honest: an audit instruction, a memory that survives resets, and fresh-eyed verifiers.
- Nº 028 Keep a growing knowledge base accurate Agents & Automation · Practitioner
Wrong agent answers usually trace to the files the agent reads. The four ways a growing knowledge base drifts from reality, and the habits (a router file, read-only audits, scheduled pulls, backtracking) that catch the drift.
- Nº 029 Loop the agent until the work passes Agents & Automation · Practitioner
A rerun loop makes the agent redo its own work until a check passes. Script the repetitive half of a skill, end it with a pass or fail verdict, wrap both in a loop, and keep a human at the checkpoints where errors are expensive.
- Nº 030 Trim the instructions your model outgrew Prompting & Context · Practitioner
Audit Claude Code instructions, preserve project requirements, and test a smaller setup against the work you already trust.
- Nº 031 Why AI makes slop and how to catch it Practice · Broad
Models got good where the work grades itself, and they aim at the most likely answer, which in design and writing is the average one. The fix: break your quality standard into checkable rules and keep human judgment for taste.
- Nº 034 Split big AI tasks into steps and checks Agents & Automation · Broad
One big question in one chat makes the model decide, research, write, and grade itself in a single pass. Map the work instead: parallel research jobs, a checker that did not write the answer, a merge, and your approval before anything expensive.
- Nº 035 Score your agent on known good answers Building with AI · Practitioner
One successful run proves an agent worked once. Collect real examples with answers a person already judged good, grade each run with a script or a judging model, and rerun the set after every change so you know whether it helped.
- Nº 038 Delegate to your agent in stages Agents & Automation · Broad
Give an agent one job, limit its tools, and check its work before granting more independence. Keep a human owner responsible for each automation.
- Nº 050 Keep Claude automations working Agents & Automation · Practitioner
Turn a tested task into a reusable skill, choose where it runs, and catch failed work before it wastes more time.
- Nº 052 Learn a work skill with AI Practice · Broad
Choose a task, give AI a specific tutoring job, and check what you can do without help. Use recurring mistakes to plan practice and spaced review.
- Nº 053 Compare AI agents on your own work Agents & Automation · Practitioner
Compare agents on one repeatable task, check the tools each can use, and keep your skills usable when you switch.
- Nº 054 Make skills improve after each run Agents & Automation · Practitioner
Use failed runs to repair skill descriptions, scripts, and checks. Test each change before keeping it, with Harness Firmware as a working example.
- Nº 055 Build a skill from an approved example Agents & Automation · Practitioner
Turn a result you already like into a reusable Codex skill. Define its task, decide where judgment belongs, and test it on fresh input.
- Nº 056 Use Jev for fast AI decisions Building with AI · Practitioner
Define the choices, scores, and yes-or-no questions Jev can answer, then use the results to route work. Compare examples from four videos, recognize tasks that need deeper context, and test accuracy, cost, and speed before automating.
- Nº 057 Give your coding agent a finish line Agents & Automation · Practitioner
Set a coding agent a result, a check it can run, and a clear stopping point so a long task ends with evidence you can review.
- Nº 060 Improve your Claude Code workflow Practice · Practitioner
Find why an AI task needs repeated corrections, change one cause, and compare the results before keeping the new workflow.
- Nº 061 Write smaller Claude skills that work Agents & Automation · Practitioner
Turn a repeated correction into a focused Claude Code skill. Choose when it runs, test its output, and remove instructions that add no value.
- Nº 062 Choose AI changes worth your time Practice · Practitioner
Compare a proposed AI workflow change with your current process, including setup, correction, maintenance, and the time you spend checking results.
- Nº 063 Build an AI setup for one work task Agents & Automation · Practitioner
Choose one recurring task, give an existing agent your files and procedures, and check the result. Use Harness Firmware to keep the verified setup with your project.
- Nº 064 Build software around business rules Building with AI · Practitioner
Define what the app should do, agree on the names used in the business, and check the agent's work with sample data.
- Nº 065 Review a visual plan before you build Prompting & Context · Practitioner
Use a visual brief to compare options, settle missing decisions, and check what Claude needs before it starts a larger build.
- Nº 067 Build a personal tool with Claude Building with AI · Practitioner
Turn a frustrating task into a small tool: filter the data, check model judgments, and keep the files needed to rebuild it.
- Nº 068 Five questions before you build with AI Practice · Broad
Answer five questions before asking Claude to build: the result you want as a number, the smallest first version, what to leave out, which parts must work, and what slows you down.