AGENTIX · HOW WE BUILD PROCESS & STANDARDS / 2026
§ How we build

We diagnose before
we prescribe.

No system we've built has reached production without a pass/fail eval score. That isn't a policy, it's the only responsible way to deploy AI into a business that depends on it.

100%ship with a pass/fail eval
2engagement models
30-daysupport on every build
Day 1you own all the code
§01, Why AI projects fail

Most AI systems are
built backwards.

The model is picked first, not last. The eval is written after the fact, if at all. The deployment is optimistic. We invert all three.

01

No eval framework

The system ships with a demo that worked. Then it meets real data, edge cases and compliance, and fails 15% of prompts with no one willing to sign off. There was never a definition of "working."

02

No production architecture

A notebook that calls GPT is not a production system. Without MCP boundaries, observability and graceful fallbacks, the first unexpected input breaks everything.

03

No regression protection

The model improves, the prompt changes, the data shifts. Six months on, accuracy has quietly dropped 20% and no one noticed, there was no CI gate to catch it.

The process

No surprises.
No black boxes.

Every phase has a deliverable you review and approve before the next begins. The eval harness is built in parallel with the system, never bolted on after.

FIG.01, The Engineering Program, phase by phase
YOU REVIEW & APPROVE THE DELIVERABLE BEFORE EACH NEXT PHASE BEGINS
01
Discovery
1–2 days
Written brief
02
Architecture
2–3 days
Approved design doc
03
Build
By scope
Working epics
04
Eval & CI Gate
Parallel
Passing test suite
05
Deploy
1–2 days
Production release
06
Handoff
1 day
Docs + ownership
Agentix Rapid, the fast track
01
Scope Call 30 min

Define the automation boundary, agree the success criterion, confirm timeline.

02
Build 2–5 days

Focused build in your stack, QA included. You review a working demo, not a slide deck.

03
Deploy & Ship Same day

Production deployment, self-hosted, full ownership transferred on day one.

§02, Two engagement models

Match the model
to the problem.

Both include full ownership, eval testing and production deployment. They differ in scope, timeline, and what "production" means for the problem.

MODEL 01

Engineering Program

Custom architecture, full engineering practice.

  • Full discovery & requirements phase
  • System architecture document, approved before build
  • Multi-agent system or agentic pipeline from scratch
  • Complete eval harness, must pass before production
  • CI regression gate in your pipeline
  • Full observability: LiteLLM + Langfuse from day one
  • Architecture docs + operational runbook
  • 30-day post-handoff support
Multi-week · scope sets duration · you own everything
Engineering Upgrade service →
MODEL 02

Agentix Rapid

One targeted automation, self-hosted, live in days.

  • Scope call to define the automation boundary
  • Single-focus automation built in 2–5 days
  • QA and functional testing before delivery
  • Production deployment to your infrastructure
  • Self-hosted, your data never leaves your environment
  • Full code ownership on delivery
2–5 days from scope sign-off · 10 documented builds in the portfolio
See the automation portfolio →
§03, The engineering standard

Eight things that
are never optional.

These apply to every system, in every engagement, at every size. They are what separate a prototype from production software.

FIG.02, Jaadu observability & analytics dashboard (real product screenshot)
Jaadu engineering analytics dashboard showing build health, context and output metrics

The standards aren't a manifesto, they're measured. What that rigor produces, in named systems and for named clients:

  • £25K/yr receptionist cost replaced for A&A by a Voice AI agent, plus ~20 hrs/week of staff time saved.
  • 12h → <5min VistaGPT cut Power BI PBIR report builds from twelve hours to under five minutes across 5 production clients.
  • ~3,953 commits across 26+ repos, 4 production systems plus 1 in active development. This is depth, not a deck.
See the full evidence →
01MCP as system boundary

All external I/O routes through a typed gateway. A misconfigured agent cannot reach production data unintentionally.

TAFI: 11 MCP tools · Orions: read-only gateway · VistaGPT: 8 services

02Eval harness before production

A pass/fail suite must exist and pass before any deployment. If it can't be tested, it won't be shipped.

TAFI: QA 100, 3 clean runs · VistaGPT: 95.3/100 · Orions: 7 golden fixtures

03CI regression gates

Every merge is blocked if it degrades performance, preventing the slow "works on my machine" drift that kills AI systems.

Orions: CI blocks PR if precision drops >5pp or ECE >0.15

04Zero-hallucination layer

Deterministic retrieval and schema constraints enforce grounding before any LLM writes. Architectural, not prompt-based.

VistaGPT: 6 parallel ChromaDB stages + reconcile before SQL

05Human approval gates

Every agentic system has defined checkpoints where a human confirms. Bypass is an explicit, named flag, never the default.

TAFI: 3 named gates · AI CompMate: Observer → Partner ladder

06Full observability from day one

Traces, per-stage latency, cost-per-query and error rates, instrumented before launch, not when it breaks at 2am.

LiteLLM + Langfuse across all systems · Prometheus + OTel on Orions v2

07LiteLLM unified proxy

Multi-provider routing, Claude primary, GPT fallback, in one layer. No per-service config, no lock-in, instant failover.

VistaGPT: 8 services unified · TAFI heavy/light model split

08Safe migration paths

New versions run in shadow mode beside v1. You compare outputs on real traffic before cutting over. No surprise risk.

Orions v2: DIAGNOSIS_V2 flag · compare via GET /eval/shadow-report

§04, The handoff

You own it
from day one.

Every system is delivered with the documentation and infrastructure for your team to operate, extend and maintain it, without us.

Start a project
  • Production deployment, verified working, monitored from day one
  • Complete eval test suite, runnable by your team at any time
  • CI regression gate, configured in your pipeline, blocks quality drops
  • Architecture documentation, system diagram, components, decision log
  • Operational runbook, how to monitor, debug and extend
  • LiteLLM + Langfuse observability, dashboards set up and accessible
  • 30-day support window, direct access for questions and edge cases
  • Full code ownership, every line committed to your repo from day one
§ Common questions

The questions worth asking.

Do I need to provide a technical spec?

No. The Discovery phase is where we build the specification together. You explain the problem, what you're automating, what the failure mode is, what success looks like, and we write the architecture doc from there. If you already have a spec, even better.

What happens if the system doesn't pass eval?

It doesn't ship. The eval harness defines what "working" means for your system; if it doesn't pass, we fix it, that's part of the build, not a separate cost. TAFI's E13 story is the clearest example: the eval showed QA 100, but platform verification found 5 failure classes it hadn't covered. We fixed all 5 before shipping.

Can I host this myself?

Yes, and we prefer it. Self-hosted means you own the data, model calls don't route through any third-party logging layer, and you're not paying us usage fees indefinitely. We deploy to K3s on Hetzner for most systems, but can target any Kubernetes-compatible environment.

Do you offer retainers or ongoing support?

A 30-day support window comes with every engagement. Beyond that we work on a project basis, a new scope call for new work. The best relationship is a client who owns their system and returns to extend it, not one paying a monthly fee for access.

What's the smallest project you take on?

A Rapid Automation, a single, well-defined process, 2–5 days. The constraint isn't budget; it's that the problem must be specific enough to automate in that window. The 30-minute scope call will tell you whether yours fits.

Start a conversation

Tell us about
your project.

Describe the process you want to automate, the data you want to query, or the problem you want to solve. We'll tell you how we'd build it, what it would take, and the eval it would have to pass.

AGENTIX TECH · diagnose first · build second · ship with proof