01
Tools as Zod schemas
Every tool's input is a Zod schema. The model's output is parsed and validated. Invalid output triggers a repair prompt with bounded retries, not silent failure.
★ Production agentsDirect LLM · no framework8-week engagement
PRODUCTION AGENTS · TOOL-USING LLMSAgents with hard guardrails.
Schema-validated function calling, per-tool rate limits, observable traces, bounded retry budgets. The engineering view of /ai-agents — same studio, deeper plumbing.
TypeScriptAnthropicZodOpenTelemetry
Cycle
8 weeks · agent to live
Stack
TypeScript · Zod · Anthropic / OpenAI
Output
Agent runtime + tools + traces
Crossref
Companion to /ai-agents — same builds
[WHY THIS EXISTS]
Most production agents run unbounded.
No retry budget, no cost cap, no schema validation, no per-tool rate limit. The first user with adversarial input or a flakey tool triggers a runaway loop, and your inference bill goes vertical. Production agents are 80% guardrails, 20% prompt.
- Tool-call retry budgets — bounded loops, not infinite ones
- Per-tool rate limits — protect downstream APIs from agent enthusiasm
- Schema-validated tool inputs — no JSON-parse roulette
- Cost caps + observable traces — see every step, every retry, every spend
[HOW WE BUILD IT]
Direct API + Zod + telemetry.
02
Bounded retry budget
Maximum N tool calls per session, M retries per tool. The runtime kills the loop when either budget exhausts. The user gets a graceful fallback.
03
Observable traces
OpenTelemetry spans on every model call and tool invocation. You can replay any session as a trace tree — input, output, retries, cost, latency.
04
Eval-gated tools
Adding a tool runs the agent eval suite end-to-end. If the new tool breaks an existing flow, the PR doesn't merge.
[OUTCOMES AT HANDOFF]
What's live at week eight.
Bounded
Retry + cost budgets on every session
Typed
Tool I/O validated end-to-end
Traced
Every step visible in your APM
Eval-gated
New tools tested against existing flows
[ALSO WORTH READING]
Related LLM engagements.
DIRECT LLM · APPLIED KBring the problem.
Bring the problem.
We’ll bring the build.
Eight weeks, fixed price, eval suite at handoff. Direct LLM engineering on top of the K-Framework. Two Q3 slots remain.