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 1 — Discovery + schema design
- Week 2–3 — Pipeline implementation + calibration
- Week 4–5 — Hardening + 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 1 — Data inventory + UI shape
- Week 2–4 — Tile server + browser app
- Week 5–8 — NL 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 1–2 — Tool inventory + MCP schema
- Week 3–6 — Orchestration + first agent
- Week 7–10 — Evals + 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.