Two AIs, one product
Goal Navigator runs two AI systems on purpose: MATE agents own every conversation; a direct Claude pipeline owns structured planning. Not a compromise — a strategy. Because the most common thing a real product already has is an existing AI investment, and the worst pitch in the world is "first, throw yours away."
Conversation and computation are different jobs
"Add AI to the product" hides two very different problems. A coach chat needs personality, memory, streaming, session handling, cost visibility — platform concerns, solved once, reused everywhere. Route generation needs none of that: it needs strict JSON against a schema, validation before saving, and surgical updates that never overwrite a user's data wholesale. Forcing one system to do both jobs badly is how AI features end up mediocre at everything.
Where personality and sessions live
- welcome_agent greets visitors, qualifies, hands off to signup
- coach_agent answers "what's my mission?" with real progress data
- mission_agent & goal_agent support the daily loop
- Widget keys per agent · sessions scoped per user · streaming SSE
- Token costs tracked per agent on the MATE dashboard
Where correctness and data safety live
- Goal → route map: 3–6 milestones, weekly focus, daily missions
- Output validated against a JSON schema before anything saves
- Patches, never blind overwrites — small changes return structured diffs
- Refinement uses Navigator Notes — reflection becomes planning input
- Every operation logs tokens, model, and estimated cost
The context bridge — trust built server-side
The coach agent feels like it knows you because the product tells it — on the server, where the browser can't interfere.
Graceful degradation, by config
If the coach's widget key isn't configured yet, the chat falls back to the welcome agent — integration wired and testable before every piece exists. Ship the seam first.
One key, one agent, one blast radius
MATE binds each widget key to exactly one agent, and sessions are scoped per key and user — the same isolation discipline as the MCP tools.
Costs visible on both lanes
MATE's dashboard tracks conversational tokens per agent; the planning pipeline logs cost per operation. When finance asks what AI costs, the answer is a query, not a shrug.
This is the pitch, proven on ourselves
Your product probably already has some AI. The right platform doesn't replace it — it takes the conversations, leaves the pipelines, and makes both cheaper to run.Hybrid isn't a compromise; it's the architecture
More from this showcase
We don't just enable AI. We ship it.
Goal Navigator: our own product, on our own platform — live at goalnavigator.ai.
Read the story → MCP in ProductionAgents that know your data
How the conversation lane reaches product data — governed, audited, least-privilege.
Read the story → From a client engagementAI that suggests. A person who decides.
The same authorship philosophy in a client's AI-native product.
Read the story →Adding conversation to a product that already computes?
MATE is open source, and the integration playbook is battle-tested — on the product we run ourselves.
Book a Strategy Call