agent.ops@ v3.4.1
Internal agents
SyncprodOps bots, call summarizers, lead enrichment, admin tools. The busywork your team does by hand, now a job that runs on its own.
Signature
ops: (task: Brief) → Result<Action[]>stack · Claude Agent SDK · n8n
Model
Claude Opus
Latency · p95
2.1s
Cost / call
$0.018
Eval pass
96.2%
agent.rag@ v2.7.0
RAG support chat
StreamingprodChat that answers from your knowledge base, not thin air. Every answer is grounded and cited. When it is not sure, it hands off to a person.
Signature
rag: (msg: Msg, ctx: Conv) → Stream<Reply>stack · pgvector · LangGraph
Model
Claude Sonnet · pgvector
Latency · p95
1.4s
Cost / call
$0.014
Eval pass
94.1%
agent.voice@ v1.9.0
Voice agents
RealtimeprodInbound qualifying, outbound calls, booking. The agent talks, transcribes, and writes the result back to your CRM.
Signature
voice: (audio: Stream<PCM>) → Stream<Turn>stack · Vapi · Retell · WebRTC
Model
Haiku · Vapi · Retell
Latency · p95
560ms
Cost / call
$0.21 / min
Eval pass
91.8%
flow.automate@ v4.1.2
Workflow automations
AsyncprodForm-to-action chains, enrichment, lead scoring, reporting. Built on n8n, self-hosted. The manual handoffs just stop.
Signature
automate: (trigger: Event) → Run<Job>stack · n8n · Make · Zapier
Model
Routed · Sonnet / Haiku
Latency · p95
320ms
Cost / call
$0.004
Eval pass
98.4%
agent.content@ v2.3.0
Content pipelines
Multi-agentprodOne pillar becomes a week of posts, locked to your tone. The agent drafts, a senior editor reviews, you ship.
Signature
content: (pillar: Brief) → Atom[12]stack · Claude · n8n
Model
Claude Opus · Sonnet 4.6
Latency · p95
4.8s
Cost / call
$0.42 / piece
Eval pass
89.6%
agent.admin@ v1.5.4
Internal LLM tools
SyncstagingSmall web apps your ops team uses: tag records, summarize queues, batch-extract data. Grind work goes from hours to a click.
Signature
admin: (rows: Record[]) → Annotated[]stack · Next.js · Claude
Model
Haiku
Latency · p95
180ms
Cost / call
$0.0006 / row
Eval pass
95.3%
Claude Agent SDK·n8n·RAG·MCP·Voice·Evals
AI agents and workflow automation, built as code in a repo you own.
You describe the manual job in a few sentences. A senior engineer ships the agent that does it: support chat answering from your own docs, lead enrichment, internal ops agents, voice, content pipelines. Every one tested with evals before it touches live traffic, every one running on your infrastructure with your API keys.
Cancel us and the agent keeps running, because it was never ours.
Your repo, your infra, your keys · Evals before live traffic · Month to month or one-off
Two fields here. The brief below arrives pre-filled, three fields to go.
One run, traced
Watch a single run, including the part that goes wrong.
Every agent we ship traces its runs like this. Timestamps, what each step read, a retry when a system times out, and an eval gate that stops low-confidence output before a person ever has to catch it. This is what “you can trust the automation” looks like when it’s written down.
- 09:14:02
trigger · inbound email
New message in the support inbox. The agent wakes up; nobody had to notice.
- 09:14:030.4s
classify intent
Read the email, matched it to “billing question” with the categories you approved.
- 09:14:033.0s
fetch CRM record
First attempt timed out at 3s. Logged, waited, retried.
- 09:14:070.8s
fetch CRM record · retry 1
Customer record and plan pulled. The retry is in the trace, not swept under it.
- 09:14:081.1s
check policy · RAG
Searched your own policy docs and cited the paragraph it will answer from.
- 09:14:102.3s
draft reply
Wrote the answer in your support voice, with the citation attached.
- 09:14:110.6s
eval gate · score 0.92
Scored against the eval suite. Threshold is 0.85: below it, the run stops here and pages a person instead.
- 09:14:11
held for human approval
The draft waits in your queue. On day one everything holds; you loosen it per intent, category by category, when the trace has earned it.
- 09:31:47
approved · sent · logged
Reply sent, CRM updated, the whole trace stored. The person spent thirty seconds approving instead of fifteen minutes writing.
9 events · 1 retry · eval 0.92 ≥ 0.85 · human approved · full trace stored
Below the eval threshold, nothing sends without a person. Above it, you decide per category how much runs on its own, and the trace is always there to check.
The agent is a file
“Built as code” means you can read it.
This is the run above, as the file that produces it, simplified for the page. Every behaviour is a line: the trigger, the steps, the eval gate, the approval hold. Your team can read it, diff it, and revert it, because it lives in your repository next to everything else you own.
export const agent = defineAgent("support-triage", {trigger: inbox("support@you.com"),← what wakes itsteps: [classifyIntent(categories),← your categoriesfetchRecord(crm),← retries built incheckPolicy(rag(docs)),← cites your docsdraftReply(voice),← your support voice],evalThreshold: 0.85,← below this, a personapproval: "human",← loosened per categorytrace: true,← the run log above});
$ git push · deploys from your repo, on your infrastructure · evals run before traffic does
No platform login we hold over you, no workflow trapped in a vendor’s canvas. If we disappear tomorrow, this file still runs, and any engineer can pick it up.
agents.registry · what we build
The AI agents and workflow automation we build. Each shipped to a repo you own.
06 / 06 · code in your repo
The stack is yours to inspect, swap, or fork. Every choice is one a senior with about a decade can defend, with the evals to back it. One of 8 practices. Hire it alone or add more, never a forced bundle.
Map my workflow, freeAgent diagram · sanitized snapshot
The pipeline we actually ship.
AI automation services, in plain terms: a senior engineer turns a manual process into AI agents and workflow automation that run on their own. Five nodes, each with its own latency and cost. You get this back in your audit, drawn for your workflow. Evals on every node, tracing before live traffic.
Diagram v 04 · sample
- 01
Trigger
Form / Webhook
p95
80ms
cost
$0.001
- 02
Retrieve
pgvector / Pinecone
p95
120ms
cost
$0.0008
- 03
LLM
Claude Opus
p95
1.4s
cost
$0.012
- 04
Eval
Langfuse / Braintrust
p95
60ms
cost
$0.0003
- 05
Action
CRM / Slack / DB
p95
90ms
cost
$0.0005
Total p95
1.75s
Cost / call
$0.014
Eval pass · illustrative
94.2%
- Grounded answers, low-confidence to a humanillustrative
Support deflection bot
- Form to enriched CRM recordillustrative
Lead enricher
- Every call summarized and filedillustrative
Call summarizer
- One pillar into a week of postsillustrative
Content pipeline
This is what an audit reply looks like. Real diagram, real costs, real evals. No deck.
Map my workflow, freeWorkflow audit · sample finding card
What we check before an agent ships.
Every engagement opens with an audit. FAIL items become sprint one. You see all of it, including what we would not touch yet.
- FAILHallucination managementWe check grounding, confidence thresholds, and the human fallback, because those three keep wrong answers away from customers.
- FAILObservability and tracingNo tracing wired. You cannot see the prompt, context, or tool calls. Debugging is guesswork.
- WARNEval suiteZero evals. No way to catch quality slipping when a prompt changes.
- WARNVendor lock-inHardcoded to one provider. No abstraction layer. Switching means a rewrite.
- PASSData residency and securityVendor confirmed not to train on your inputs. PII scrubbing in place.
- PASSAPI key custodyKeys stay in your vault, rotated on a schedule. No shared keys in the code.
Findings like these land in your inbox in days, with the diagram. Every build then clears two QA passes before live traffic.
Map my workflow, freeFour principles.
Wired into every agent.
Most AI projects fail for the same few reasons. These four put them on the table, in writing, before an agent goes live.
- PI
You own the prompts, the code, and the infra
Prompts and code live in your repo, version-controlled. Infra runs on your accounts. Token costs pass through at provider cost. We never hold your API keys.
Principle I - PII
Evals and tracing on day one
Tracing is wired before the first live call. Every prompt change runs the evals before it ships. You see what the agent did, why, and what it cost. No black box.
Principle II - PIII
Low-confidence answers go to a human, not a guess
A confidence threshold sits on every output. Below it, the answer routes to a person, not the customer. Every claimed fact shows its source.
Principle III - PIV
Mutual NDA, and no training on your data
Signed before we look at your workflows. Vendor contracts confirmed not to train on your inputs. PII scrubbing in place.
Principle IV
Operator's mark
You can cancel any month, month to month. Most clients stay: most clients stay well past the first project.
Eval ledger · sample build · v0.1 → v1.0
Every version runs the evals. None ships without them.
Production gate · ≥ 90% pass
- v0.1Day 03
Baseline. Zero-shot Sonnet, no retrieval, no HITL.
84 tests · Senior engineer
p951.9sCost$0.01846.2% - v0.2Day 07
pgvector retrieval over your KB. Confidence threshold at 0.72.
124 tests · Senior engineer
p951.7sCost$0.01462.8%▲ 16.6 - v0.3Day 12
System prompt rewrite. Voice locked to your brand doc.
188 tests · Senior engineer
p951.6sCost$0.01471.4%▲ 8.6 - v0.4Day 18
Human fallback below 0.65 confidence. Citations surfaced.
246 tests · Senior engineer
p951.5sCost$0.01382.0%▲ 10.6 - v0.5Day 22
Router added. Haiku for tier-2, Opus for tier-1. Cost halved.
312 tests · Senior engineer
p951.4sCost$0.00987.6%▲ 5.6 - v1.0shippedDay 28
Evals past the production gate. Rolled out to 100% traffic.
312 tests · Account lead
p951.4sCost$0.00994.2%▲ 6.6
The first agent reaches production in weeks. The diagram and audit land in days.
Map my workflow, freeWhat people ask before they let an agent into the stack.
Plain answers on who owns the prompts, how we keep the agent honest, and what it costs.
You do, from the first commit. The agent is code in your repository, the prompts live in that code, and it runs on your infrastructure with your API keys. Cancel us and everything keeps running, because none of it was ever ours.
There is no rate card. You describe the workflow, we map it for free, and the map comes back with a fixed quote: a one-off build price or a month-to-month retainer, your call. Model and infrastructure costs pass straight through to you at cost, on your own accounts, with no markup.
Every run is scored against an eval suite before anything sends. Below the threshold, the run stops and a person gets it instead. On day one every action holds for human approval, and you loosen that per category only after the trace has earned it. When something does slip through, the full trace shows exactly which step went wrong, so it gets fixed in code rather than argued about.
Almost certainly. Agents connect to your CRM, helpdesk, database, inbox, and Slack through their normal APIs. Week one produces a written map of every system involved, its rate limits, and its owner, so surprises surface before the build starts rather than after.
No. It runs on its own, and the repo ships with docs written for an engineer who has never met us. Because the agent is plain, readable code rather than a locked vendor canvas, any developer you hire later can maintain or extend it.
The workflow map comes back in days and tells you exactly what the build involves. Simple workflows ship fast; nothing goes live before the evals pass on real examples from your own data, and the first stretch always runs with a human approving every output.
One step
Get your first workflow mapped, free.
Describe the manual work in a few sentences. In days you get a diagram of the automation, an eval plan, a cost estimate, the named engineer, and a price. Retainer or one-off, your call.
- 01Free diagram and audit in days
- 02A senior engineer named on day one
- 03Code in your repo, evals before live traffic
- 04Token cost passes straight to you
Rather talk first?
Book a 20-minute call with a seniorDescribe the workflow. The map comes back in days.
A few fields. One business day to a senior reply. No follow-up sequence.
Capacity is limited on purpose: seniors do the work, so we take a few new engagements at a time. The audit is how we choose.
Sealed · Read by a senior engineer
Workflow map · free
Production AI agents, not slides