Building in-house data tools? Read this first.
In-house data infrastructure gives you control, flexibility, and deep customisation. The teams that get it right move fast and build a real competitive advantage. The teams that get it wrong spend months building something their business doesn't trust — burning engineering time, inflating AI costs, and shipping answers that look right but aren't. Supper is designed to address every major risk of in-house data development. Here's what those risks actually look like.
Built with Supper, the same in-house tooling is —
Part 01
01
A raw LLM has no idea how your company defines ARR, what your pipeline stages mean, or which edge cases matter. It guesses — and it's wrong roughly 40% of the time on real enterprise schemas.
The cost compounds twice. First on accuracy: one in five queries returns a misleading result, and users have no way of knowing. Then on spend: agentic workflows re-send full context with every tool call, so token consumption balloons against query volume that was never sized for it.
Text-to-SQL accuracy — raw LLM
Accuracy rate for raw LLM-to-SQL on real enterprise schemas. Your business logic lives nowhere in the raw tables.
Multiple industry evaluations, 2025–26
Queries return a misleading result — and users have no way of knowing.
AIMultiple, 2026
Average columns in an enterprise schema. None of them encode your definitions.
Spider 2.0, ICLR 2025
02
The longer a session runs, the less accurate it gets.
Loading schema, tool results, and follow-ups pushes critical context out of reach. Accuracy drops more than 30% for information buried mid-context — and it's found in every major frontier model tested, at every input length.
It's the quiet failure mode of DIY agentic setups: nothing errors, nothing alerts. The answer just gets gradually less reliable as the conversation grows longer.
Same data, worse result. The only thing that changed was how deep into the session the question landed.
Accuracy drop, mid-context
For information buried in the middle of a long session — across every major frontier model tested.
Chroma, 2025 · morphllm.com
Accuracy when key info sits mid-session — vs. 70–75% at the start or end.
Stanford "Lost in the Middle," TACL 2024
Of enterprise AI failures in 2025 caused by context drift in multi-step tasks.
Zylos Research, 2025–26
03
Stacking skills, plugins, and MCPs onto a general-purpose model doesn't make it smarter about your data. It makes it slower, more expensive, and less reliable. Purpose-built agents — designed for a specific job — consistently outperform bloated general setups on every measurable dimension.
Wasted per session by unused skills that load into context regardless of whether they fire. Half never activate — but all of them cost.
Developer audit, AI Weekly, May 2026
For a $200/mo plan to hit usage limits when bloated with plugins, MCP servers, and skills — versus the expected 5-hour window.
Claude Code Cleanup, Mar 2026
Before one enterprise canceled coding-agent licenses org-wide after token costs consumed the annual AI budget ahead of schedule.
Fortune / Dapta.ai, June 2026
"Let me check… let me verify… let me try again…" — the reasoning-narration loop burns context budget on internal monologue before any real work is done.
Accuracy: domain-specific agents vs. general-purpose LLMs on identical enterprise tasks. Specialisation — not a bigger model — drives the gap.
Aisera CLASSic Framework, ICLR 2025 Workshop
Lower cost per task for purpose-built agents vs. general-purpose agents achieving the same accuracy. Precision reduces token waste at the source.
Aisera CLASSic Framework, ICLR 2025 Workshop
Part 02
04
The fix isn't a better model — it's better context. Encode your business logic once and every answer is grounded in it, automatically. The improvement isn't marginal; it's the difference between a coin flip and production-grade reliability.
Without semantic layer
LLM guesses at your business logic.
~40%
With Supper's semantic layer
Every query runs through your definitions.
85–95%
Accuracy jump across 40 real business questions — semantic layer vs. raw schema.
AtScale, published benchmark 2024
Accuracy gain from raw tables to governed semantic definitions.
dbt Labs internal benchmark, 2026
Accuracy in production deployments with a properly encoded semantic model.
DataLakehouseHub, 2026
05
Supper isn't a replacement for in-house data tooling. It's the infrastructure layer that makes in-house tooling actually work — faster to build, cheaper to run, and accurate enough to trust.
Supper's integration layer connects directly to your existing data sources — no bespoke pipelines, no months of ETL. Your team moves from data access to working product faster, with less infrastructure to maintain.
Move faster · Spend less
The semantic model is the most complex piece of any agentic data workflow — encoding your business logic, metric definitions, and edge cases once, so every agent and query is grounded in the same verified truth. Build on it. Don't rebuild it.
Accurate · Consistent · Maintainable
Supper's MCP connection embeds into coding agents for technical builders, or surfaces through general-purpose LLM interfaces for business users — the same semantic layer, accessible to everyone, in the tools they already use.
Builders · Business users · One source of truth
06
You've seen where the DIY path breaks. Here's the same job done with Supper — line for line. Every failure mode above is already solved at the layer beneath your tools, so your team builds on trusted answers instead of rebuilding the foundation by hand.
Built in-house. Backed by Supper.
Semantic layer, Forward Deployed Analysts, and a full audit trail — everything you need to ship in-house data infrastructure your business actually trusts. Verified answers in weeks, not months.
supper.coSources: Chroma (2025) · Stanford/TACL, Liu et al. (2024) · Zylos Research (2026) · AtScale (2024) · dbt Labs (2026) · Spider 2.0/ICLR (2025) · AIMultiple (2026) · Gartner (2026) · MCP vs RAG Benchmark arXiv:2511.23281 · Aisera CLASSic/ICLR (2025) · AI Weekly (2026) · Fortune/Dapta.ai (2026) · Claude Code Cleanup (2026)