PRX/03 · SERVICE 02 · CUSTOM AGENTS
SHEET 02 OF 03 · LOOP / PRX-S2
[ 03.2 / Agents ]
000 %
Service 02 of 03 · 8-14 week engagements Sheet PRX-S2 / Bounded-autonomy agents Filed 05.09.26
[ 03.2 ]Service · Agents

Service 02 / Agents Custom AI agents, with bounded autonomy.

We build custom AI agents for teams who need a piece of work done end-to-end - research, drafting, operating a real system - by something more capable than a prompt and more accountable than a black box. Scoped, observable, owned by you.

FIG. 03.2 / AGENT LOOP - PERCEIVE / PLAN / ACT / REVIEW PRX-S2 · REV 04.30 BOUNDED · OBSERVABLE · INTERRUPTIBLE SHEET 02 / 03 AGENT CORE / LLM [ 01 ] PERCEIVE read · search · query tools · web · vector store [ 02 ] PLAN decompose · sequence budget · checkpoint [ 03 ] ACT tool calls · writes scoped · approved [ 04 ] REVIEW eval · trace · diff human / auto reviewer GUARDRAILS KILL SWITCH SCOPE: explicit allowlist of tools · MAX STEPS · MAX SPEND · TIMEOUT EVERY STEP TRACED · REPLAYABLE
[ 03.2.A ]Brief

A custom AI agent is the right tool when the work isn't a single prompt or a single pipeline - it's a small project that has to happen reliably, at volume, with judgement. Research a prospect across twelve sources and write a one-page brief. Reconcile a vendor invoice against three systems and flag the discrepancies. Draft a contract red-line, cite the clauses, and route it for review.

We do not ship "a chatbot." We ship a scoped agent: a clearly-bounded loop that perceives, plans, acts, and reviews, with an allow-list of tools, a step budget, a spend cap, an auditable trace, and a human-in-the-loop where the stakes warrant one.

Bounded autonomy is the whole game. The agent is allowed to be smart; it is not allowed to be unobservable, unstoppable, or unbounded. Every Praxis agent ships with a kill switch, a replay tool, and a runbook your team can use to inspect any decision after the fact.

[ 03.2.B ]What we build

  • Research agents. Multi-source briefs on prospects, candidates, vendors, or markets - with citations, structured output, and a one-pager you can hand to a partner.
  • Drafting agents. Long-form documents in your voice and your structure: contracts, RFP responses, case files, exec summaries.
  • Operator agents. Persistent agents that drive real systems: book the meeting, file the ticket, open the PR, post the update, on a schedule or on demand.
  • Reviewer agents. The other side of the loop: agents that grade, redline, and flag - against your style guide, your policies, your contracts.
  • Internal copilots. A team-shaped chat surface that knows your wiki, your CRM, and your codebase, with retrieval that doesn't hallucinate.

[ 03.2.C ]How we work

Engagements run 8 to 14 weeks. Discovery (2 weeks) maps the task end-to-end with an operator, defines the eval set, and writes the scope contract. Build (4 to 10 weeks) is the founder writing the loop, the tools, the guardrails, and the eval harness against real data. Handoff (2 weeks) sits with your team, transfers credentials, walks through the trace explorer, and rehearses the kill switch.

Every agent runs on your models, your credentials, your infrastructure. We hand back the prompts, the tools, the eval set, and the diagrams. You can fork, modify, and extend without us in the loop.

[ 03.2.D ]Engagement spec

The shape of the work.

FIG. 03.2.D / Spec sheet
Sheet 02 of 03
Duration
8-14 weeks
discovery → build → handoff
Pricing
Fixed-price
per phase, no hourly billing
Autonomy
Bounded
allowlist · budgets · timeouts
Eval set
≥ 200 cases
graded weekly through build
Stack
Yours
runs on your accounts and keys
Models
Multi-vendor
openai · anthropic · local
Trace
Every
step
replayable from dashboard
Kill switch
Always
one click halts every agent
[ 03.2.E ] Testimonial · Case file 07
"Our research analyst used to spend Tuesday writing prospect briefs. Now the agent writes them overnight, cites every claim, and our analyst spends Tuesday talking to the prospects. The trace explorer is the reason we trust it."
K. Vassilakis · Managing Partner B2B advisory · 24 staff · London / Athens
[ 03.x ]Other services

Three disciplines.
One studio.

Sheet 03 of 03
Begin / 30-min discovery

Bring us a
task.

Describe one piece of work that has to happen reliably, at volume, with judgement. We'll tell you whether it's an agent shape, a pipeline shape, or neither.

No deck. No pre-qualification. Just a conversation.