[agents](https://carteblanche.com/index.md?kind=agent) / [code](https://carteblanche.com/index.md?category=code) # database-design-database-architect what it does Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures. Masters SQL/NoSQL/TimeSeries database selection, normalization strategies, migration planning, and performance-first design. Handles both greenfield architectures and re-architecture of existing systems. Use PROACTIVELY for database architecture, technology selection, or data modeling decisions. tools it asks for Every tool, since it names none by wshobson · version 1 · license MIT We imported this agent from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/database-design-database-architect) Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/wshobson/agents/blob/4bde3168b43c0655c4d00ea2726e631719908a6d/plugins/database-design/agents/database-architect.md) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/database-design-database-architect/download) ## Compare the answers Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1 Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself. [Compare the answers](https://carteblanche.com/skills/database-design-database-architect/compare) ## The models 2 models Claude Sonnet 5.5 made by Anthropic claude-sonnet-5-5 · revision not reported by the provider 1 try per case · tested 7 Nov 2026 GPT-6.1 Sol made by OpenAI gpt-6.1-sol · revision not reported by the provider 1 try per case · tested 7 Nov 2026 ## The tasks written by Carte Blanche **example-1** “I'm building a fleet-tracking SaaS. About 50k vehicles each send GPS and engine telemetry every 5 seconds. Customers need live maps, 90-day historical playback, and monthly trip and fuel reports. We also need relational data for accounts, drivers, vehicles, and billing. Which database technologies would you pick for each part, and how would you model the main tables or collections, partition the telemetry, and handle retention? Our team is small and already knows Postgres.” **example-2** “Our Rails monolith has a single Postgres 12 database with an orders table of about 400M rows. It's slow, and the table mixes order headers, line items stored as JSONB, and status history in an array column. We want to normalize it without downtime. Can you propose a target schema, indexing and partitioning strategy, and a phased migration plan (dual writes, backfill, cutover, rollback) that keeps the app online?” ## Install Download the .zip and unzip it. Put `database-design-database-architect.md` here: Claude Code · `~/.claude/agents/` · Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others. Cursor · `~/.cursor/agents/` · Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for. Codex · Codex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there. Keep its license file beside it, as `database-design-database-architect.LICENSE`: a name that doesn’t end in .md, since every .md file there is read as an agent. Then start a new session and ask for it by name. Folders checked 6 November 2026. Or [install from your agent](https://carteblanche.com/connect.md): ask it to install `database-design-database-architect` from Carte Blanche. ## Badge for your README Carte Blanche: Verified Paste this into the agent’s README. It links to this page, and shows how the listing stands whenever it’s loaded. ``` [![Carte Blanche](https://carteblanche.com/badge/database-design-database-architect.svg)](https://carteblanche.com/skills/database-design-database-architect) ``` ## About this test - **tested**: 7 Nov 2026 - **version tested**: v1 - **cases**: 2 - **tries per case**: 1 try per case - **run without the agent**: yes - **cases written by**: Carte Blanche - **size**: 16258 characters What this shows, and what it doesn’t How 2 models answered these 2 requests, with and without the agent. It says nothing about other models, and it doesn’t limit what your own agent can do. The answers were written without tools: the agent’s instructions were the system prompt, and it read no file and ran nothing. [How we test](https://carteblanche.com/how-it-works.md)