Geonix

Three packages, fixed scope.

Pick the closest match. We'll tighten scope on a 20-minute call.

Foundation

Production-ready ingestion + calibration pipeline on the data you already collect.

TODO_USER_COPY: 150-word description of what Foundation covers, when to hire it, representative tech stack.

Talk about this package →

Deliverables

  • Schema and storage layout (Parquet / GeoParquet) committed to your repo
  • Streaming or batch ingestion with backpressure + retries
  • Calibration sprint on a representative sample dataset
  • Per-stage timings + correctness check suite, wired to your observability stack

Timeline

  • Week 1Discovery + schema design
  • Week 2–3Pipeline implementation + calibration
  • Week 4–5Hardening + handoff

You provide

  • Sample data access
  • Calibration target
  • Reviewer time

I provide

  • Code + infra-as-code
  • Methodology writeup
  • Two follow-up sessions

FAQ

Can you work with our existing storage?
Yes — Parquet, Iceberg, Delta, plain object storage, or your warehouse.
Do you do operational handoff?
Code + runbooks + two follow-up sessions. Longer support contract optional.

Visualization & Query

TB-scale data made browsable: tile servers + NL query over your warehouse.

TODO_USER_COPY: 150-word description of Visualization & Query.

Talk about this package →

Deliverables

  • MVT tile server (Rust or Go) backed by your Parquet/GeoParquet
  • Browser app with MapLibre + deck.gl, configurable layers
  • NL → SQL layer wired to DuckDB or your existing warehouse
  • Latency budget + caching strategy

Timeline

  • Week 1Data inventory + UI shape
  • Week 2–4Tile server + browser app
  • Week 5–8NL query layer + hardening

You provide

  • Read access to data
  • Domain reviewer
  • Auth/SSO requirements

I provide

  • Code + infra-as-code
  • Performance report
  • Two follow-up sessions

FAQ

What zoom levels are supported?
All of them. We pre-aggregate where it makes sense and stream raw at high zooms.
Can the NL query layer use our schema?
Yes — it reads your information schema and produces typed SQL against your warehouse.

Agentic Layer

Domain-specific agents and the orchestration substrate they run on.

TODO_USER_COPY: 150-word description of Agentic Layer.

Talk about this package →

Deliverables

  • MCP server exposing your domain tools to any agent runtime
  • Agent orchestration with typed tool I/O, retries, and traces
  • Eval harness for agent behaviors with golden test sets
  • Cost + latency telemetry per agent run

Timeline

  • Week 1–2Tool inventory + MCP schema
  • Week 3–6Orchestration + first agent
  • Week 7–10Evals + telemetry + hardening

You provide

  • Domain expert time
  • Existing tools/APIs
  • Eval criteria

I provide

  • Code + IaC
  • Eval report
  • Two follow-up sessions

FAQ

Do you use a specific agent framework?
MCP + your choice of runtime (Claude Agents SDK, custom). I avoid lock-in.
How do you measure agent quality?
Golden set + adversarial set + cost/latency per run, all in the eval harness.