Custom AI agents — Atlas (sales), Drafter (legal), Ledger (finance) — that work alongside your team, take real actions in your tools, and check in with humans when it matters. The flagship of the Sitect AI stack, built for businesses ready to put AI to work.
Most teams confuse them. The difference matters because they cost different amounts, take different times to build, and solve different problems. Here's how we draw the line.
Waits for a question. Answers it from a knowledge base. Sometimes books a meeting if you ask nicely. Doesn't initiate anything.
Sits next to a person doing a job. Drafts the email, summarises the meeting, suggests the next action — but a human reviews and decides.
Given a goal, breaks it into steps, picks tools, executes, checks the result, retries, and asks for human help at high-stakes decisions. Works while you sleep.
We dog-food every agent before we sell it. The eight below run our own sales, legal, finance and ops. Each can be re-themed and re-trained for your business in 6–10 weeks.
Qualifies inbound leads, enriches profiles, scores fit, drafts outreach. Books discovery calls into a real human's calendar.
Drafts proposals, MSAs, NDAs and contracts. SA-legal-aware. Always human-approved before send. Tracks redlines.
Reads invoices, matches POs, drafts dunning emails, reconciles Yoco/EFT. Stops at R10k+ for human approval.
Handles WhatsApp + IG support 24/7. Escalates anything spicy to humans within 4 hours with a context summary.
"What did we agree with this client in March?" Answers internal staff questions from your knowledge base, with citations.
Researches accounts before sales calls. News, hires, funding, competitors. Produces a 1-pager briefing 30 min before each meeting.
New client signed? Onboarder provisions accounts, sends welcome pack, schedules kick-off, sets up Slack channel, files contract.
Runs FICA checks on new clients. Verifies SA ID, proof of residence, CIPC. Flags anything weird for human eyes.
Every Sitect agent ships with these six superpowers. They're the difference between "an LLM call" and "an autonomous worker you can trust with real work."
Given a goal, the agent plans a sequence of steps, executes them, and adjusts the plan as new information comes in. Not a single LLM call — a thought process.
Reads from and writes to your real tools — CRM, accounting, calendar, payment, email, Slack, your own APIs. Every tool call is logged and replayable.
Short-term working memory across the task. Long-term episodic memory across tasks — the agent remembers what worked, what failed, what each client prefers.
When a tool fails or a step doesn't work, the agent notices, re-plans, and tries a different approach. Up to 3 retry attempts before escalating to a human.
Configurable per-action: agents act autonomously up to a threshold (e.g. send R<10k invoices), then require a Slack thumbs-up for anything bigger.
Every thought, tool call, decision and action stored forever, replayable. POPIA-compliant retention. When something goes wrong, you can replay the exact run.
Every Sitect agent runs the same five-stage loop. Plan → choose tool → call → reflect → repeat or finish. The loop is what separates an agent from a single LLM prompt.
"Qualify L-3417"
[enrich, score, decide]
clearbit.enrich(...)
score = 87, proceed
done(opp_created)
This is a real run of Onboarder, the agent that handles new-client setup at Sitect. Triggered when a contract is signed in DocuSeal. Total elapsed: 47 seconds. Zero human involvement until the welcome call.
Every Sitect agent comes with the same scaffolding. You own all of it — code, configs, prompts, audit trail. Run it on your infra forever.
Name, voice, role, constraints, escalation rules. Written in plain markdown so your team can refine it without a developer.
JSON-Schema for every tool the agent can call. Auth tokens stored in your vault. Each tool tagged with cost + criticality.
Working memory in Redis · long-term in your Postgres/vector DB. Cleanable per-user for POPIA right-to-be-forgotten.
Pending approvals land in a dedicated Slack channel — thumbs-up to approve, thumbs-down to reject, reply with text to send back to the agent.
Every thought, tool call, result, decision. Searchable by run-id, agent, user, time. Replay any past run end-to-end. POPIA-compliant retention.
Markdown runbook for the top 12 incident types. 3-hour live training session. 90 days of Sitect on-call hand-off, then your team takes over.
Most of the work is in the front (defining the job clearly) and the back (training your team to supervise). The middle is the actual build, which is the smallest piece.
What's the agent's role? Boundaries? Tools needed? KPIs? You write its "job description" with us. Signed off before any code.
Wire up the tools the agent will use. Provision memory store. Define POPIA boundaries. Auth tokens in your vault.
System prompt drafted, approval rules configured, eval suite built. Agent runs in shadow mode against real data.
Agent goes live to a closed pilot. Heavy human supervision. We tune from real failures daily.
Full traffic. 90 days of Sitect on-call hand-off. Your team trained. Approval gates progressively relaxed.
Aggregated across our deployed agents. Your numbers will be yours — these are the order-of-magnitude bracket to plan against.
Build fee is fixed in writing. Variable cost = LLM tokens + cloud (typically R 1.5k–R 8k/month) billed direct. No per-agent platform fee. You own everything.
If yours isn't here, send us the job description. We'll come back with a build plan in 48h. No sales pitch.
claude-3.5-sonnet for reasoning and gpt-4o-mini for cheap routing calls. Can swap to Gemini, Llama 3 on-prem, or any OpenAI-compatible endpoint with a config change. For sensitive industries (finance, legal, health) we deploy on-prem options.Write down a job your team does repeatedly — qualifying leads, drafting proposals, handling claims, onboarding clients. Send it to us. Within 5 business days we'll come back with an agent design document: tools needed, build cost, indicative timeline, and three reasons we might be wrong about it being worth automating.