Service / AI
AI agents that do the work, and show it.
Agents that plan, call tools and complete multi-step work in your systems, with the model's suggestions separated from the decisions code makes.
[ 01 ]The short answer
What is AI Agent Development?
AI agent development is building software that uses a language model to plan and carry out multi-step tasks: reading context, calling tools and APIs, and acting in your systems. The hard part is not the loop but the boundaries. We keep the model to judgement and let deterministic code make the consequential decisions, scope every tool to least privilege, check inputs for prompt injection, and give people a console to watch and overrule. That is what gets agents past the pilot.
What you get
- Agent service with typed tools
- Policy engine and decision thresholds
- Operator console with override
- Scenario and red-team evaluation suite
- Audit log and observability dashboards
[ 02 ]What we build
The pieces, built to last.
- 01
Tool-using agents
Agents that call your APIs, databases and SaaS tools through typed, permission-scoped functions.
- 02
Multi-agent systems
Planner, worker and reviewer agents that split a job, with a shared state you can inspect.
- 03
Decision boundaries
The model scores and drafts; code applies thresholds, policies and limits. The boundary is where safety lives.
- 04
Human-in-the-loop consoles
A live view of every run with the model's reasoning, and one-click approve, edit or overrule.
- 05
Memory and context
Short-term state per task and long-term memory across sessions, with sources kept for every fact.
- 06
Agent evaluation
Scenario suites, trajectory checks and red-team cases run on every change before it reaches users.
[ 03 ]Where it pays off
Where it earns its keep.
- 01
Sales development
Qualify inbound leads across chat, email and voice, and book the meeting when the rubric says so.
- 02
Recruiting and HR
Screen applications against a role and decide routine requests against written policy, with escalation.
- 03
Finance operations
Reconcile, chase and categorise with an agent that drafts and a ledger rule that posts.
- 04
Research and diligence
Gather, read and summarise sources with citations, so analysts start from evidence, not a blank page.
[ 04 ]How we deliver
Four steps, one team, start to finish.
The same people scope it, build it and stay after launch. Timings are typical for a first release; we agree yours after the deep dive.
- 01Week 1
Find the decision
We pick the decision or task worth automating, measure how it is done today and agree what better means in numbers.
- 02Week 1 to 2
Build the eval first
A labelled test set from your own data comes before any prompt or training run, so every change is scored, not argued.
- 03Weeks 2 to 10
Build with guardrails
Models suggest, code decides. Permissions, injection checks, human override and audit logs are part of the first version.
- 04Ongoing
Ship and improve
We launch to real users, watch cost, latency and quality per request, and feed failures back into the eval set.
[ 05 ]Stack
Tools we reach for.
Chosen per project, and we work in yours. Nothing here is a lock-in: you own the code and the accounts.
- Claude
- GPT
- Gemini
- LangGraph
- PydanticAI
- OpenAI Agents SDK
- Model Context Protocol
- Temporal
- Postgres
- Cloudflare Workers
- Langfuse
[ 07 ]Further reading
Problems we found, and how we would solve them.
- AI agents3 min read
Why AI agent pilots stall before production
ProblemAgent pilots impress in demos and stall before production because nobody can show they work, limit what they can do, see what they did, or overrule them.ProposalDraw a hard decision boundary: the model scores and drafts, deterministic code decides and acts, every step is logged with its reasoning, and a person can overturn any decision in one click.Read the proposal - AI security3 min read
Prompt injection is an architecture problem
ProblemAny agent that reads untrusted content and can act can be steered by instructions hidden in that content, and no prompt or filter reliably separates data from commands.ProposalAssume injection will happen and limit what it can achieve: keep untrusted content away from privileged decisions, give tools least privilege, put consequential actions behind code-level checks, and break the path to exfiltration.Read the proposal - AI security3 min read
MCP servers are your new supply chain
ProblemAgents trust tool descriptions and outputs from MCP servers they install like packages, so a poisoned description, a compromised server or an over-privileged token can steer or rob them.ProposalPut an MCP gateway between agents and servers: pinned and reviewed tool manifests, per-user scoped tokens, sandboxed local servers, output sanitising, egress allowlists and a full audit log.Read the proposal
[ 08 ]FAQ
Questions buyers ask.
Mostly governance and integration, not model quality: no evaluation set, tools with too much power, no audit trail and no way for a person to intervene. We build those first. Our article on why pilots stall is linked below.
Yes, for actions inside limits you set in code: amounts, recipients, record types. Anything outside those limits goes to a person, and the agent says why.
Whichever clears your evaluation set at the best cost and latency. We design agents to swap models without rewriting them.
[ 09 ]More AI services
- Custom AI Model DevelopmentA model trained on your data, owned by you.
- LLM Fine-Tuning and DistillationFrontier quality at a fraction of the cost.
- AI Workflow AutomationHours of back-office work, done in minutes.
- RAG DevelopmentAnswers from your documents, with citations.
- AI Memory and Knowledge GraphsAI that remembers what your organisation learned.
- MCP Server DevelopmentYour product, usable by every AI assistant.
- Voice AI AgentsEvery call answered, qualified and logged.
- Document AI and Intelligent Document ProcessingPaperwork turned into clean, checked data.
- Private LLM DeploymentAI on your infrastructure, data never leaves.
- LLMOps, Evaluation and GuardrailsKnow your AI works before customers find out.
- Predictive ML and ForecastingDecisions made on what will happen next.
One company at a time