--- title: "Give Claude Code a map of your Airtable bases without an API connection" description: "Export Airtable schemas, status definitions, and active records to Markdown, so Claude Code can read your data model and draft from current records." canonical: "https://scalewithsearch.com/articles/claude-code-with-airtable" date: "2026-01-28" modified: "2026-09-25" --- ## Site navigation - [Scale With Search](https://scalewithsearch.com/) - Real estate - Real estate - [Real estate](https://scalewithsearch.com/for/real-estate) - Work - Start here - [Send your brief](https://scalewithsearch.com/work#send-your-brief) - [Prepare your six-question brief](https://scalewithsearch.com/work#prepare-your-six-question-brief) - Build - [Site build, content library with SEO, signal desk](https://scalewithsearch.com/work) - For your business - Trades and home services - [Auto body and collision shops](https://scalewithsearch.com/for/auto-body-and-collision-shops) - [Foundation and home repair contractors](https://scalewithsearch.com/for/foundation-and-home-repair) - [Garage door and fencing contractors](https://scalewithsearch.com/for/garage-door-and-fencing-contractors) - [HVAC contractors](https://scalewithsearch.com/for/hvac-contractors) - [Janitorial and commercial cleaning companies](https://scalewithsearch.com/for/janitorial-and-commercial-cleaning) - [Locksmiths](https://scalewithsearch.com/for/locksmiths) - [Moving companies](https://scalewithsearch.com/for/moving-companies) - [Pest control companies](https://scalewithsearch.com/for/pest-control-companies) - [Plumbing and electrical contractors](https://scalewithsearch.com/for/plumbing-and-electrical-contractors) - [Restoration and water or fire damage companies](https://scalewithsearch.com/for/restoration-and-water-fire-damage) - [Roofing companies](https://scalewithsearch.com/for/roofing-companies) - [Towing companies](https://scalewithsearch.com/for/towing-companies) - [Tree services and landscaping companies](https://scalewithsearch.com/for/tree-services-and-landscaping) - [Solar installers](https://scalewithsearch.com/for/solar-installation) - [General contractors](https://scalewithsearch.com/for/general-contractors-and-construction) - [Paving, concrete, and flooring contractors](https://scalewithsearch.com/for/paving) - Practices and professional services - [Bookkeeping and tax practices](https://scalewithsearch.com/for/bookkeeping-and-tax-practices) - [Dental practices](https://scalewithsearch.com/for/dental-practices) - [Family and criminal defense law firms](https://scalewithsearch.com/for/family-and-criminal-defense-law-firms) - [Med spas and aesthetics practices](https://scalewithsearch.com/for/med-spas-and-aesthetics) - [Personal injury law firms](https://scalewithsearch.com/for/personal-injury-law-firms) - [Veterinary clinics](https://scalewithsearch.com/for/veterinary-clinics) - [Gyms and fitness studios](https://scalewithsearch.com/for/fitness) - [Therapy and outpatient health practices](https://scalewithsearch.com/for/therapy-and-outpatient-health) - [Medical billing companies](https://scalewithsearch.com/for/medical-billing) - [Insurance agencies](https://scalewithsearch.com/for/insurance-agencies) - [Financial advisors](https://scalewithsearch.com/for/financial-advisors) - [Property management companies](https://scalewithsearch.com/for/property-management) - [Recruiting and staffing agencies](https://scalewithsearch.com/for/recruiting-and-staffing) - [Architects and interior designers](https://scalewithsearch.com/for/architects-and-interior-designers) - [Logistics and supply chain companies](https://scalewithsearch.com/for/logistics-and-supply-chain) - Agencies, MSPs, and manufacturing - [IT and managed service providers](https://scalewithsearch.com/for/it-and-managed-service-providers) - [Machine shops and precision manufacturers](https://scalewithsearch.com/for/machine-shops-and-precision-manufacturing) - [Marketing agencies and freelancers](https://scalewithsearch.com/for/marketing-agencies-and-freelancers) - [SEO agencies and consultants](https://scalewithsearch.com/for/seo-agencies-and-consultants) - [Small manufacturers and fabricators](https://scalewithsearch.com/for/small-manufacturers-and-fabricators) - Restaurants, shops, studios, and nonprofits - [Restaurants and hospitality businesses](https://scalewithsearch.com/for/restaurants-and-hospitality) - [Retail stores and ecommerce sellers](https://scalewithsearch.com/for/retail-and-ecommerce) - [Photographers, event planners, and travel agents](https://scalewithsearch.com/for/photographers) - [Churches and nonprofits](https://scalewithsearch.com/for/churches-and-nonprofits) - [All industries](https://scalewithsearch.com/for/) - Learn - For your office - [Office job guides](https://scalewithsearch.com/guides/) - [Browser calculators](https://scalewithsearch.com/tools/) - Start here - [How it works](https://scalewithsearch.com/how-it-works) - [Free Starter Kit](https://scalewithsearch.com/kit/business-memory-starter-kit.zip) - [Synthetic specimen](https://scalewithsearch.com/specimen/working-session-specimen.zip) - Guides - [The Complete Guide to Business Memory for AI Agents](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [The Complete Small-Business Guide to AI Agent Governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [The Complete Guide to Leaving Vendor AI Memory](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - Articles by cluster - [Business memory](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [Agent governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [Migration and ownership](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - For machines - [llms.txt](https://scalewithsearch.com/llms.txt) - [llms-full.txt](https://scalewithsearch.com/llms-full.txt) - [Machine view](https://scalewithsearch.com/?view=machine) - Company - Evidence - [Proof](https://scalewithsearch.com/proof) - Company - [About](https://scalewithsearch.com/about) # Give Claude Code a map of your Airtable bases without an API connection. Airtable is your project database. It holds the client list, the content calendar, the product roadmap, and the hiring pipeline, each structured, linked, and filtered the way you need. Claude Code cannot see any of it. When you ask for a project update, a pipeline review, or a client status check, you explain data that already exists in Airtable. You paste tables. You describe how fields relate. You explain what "In Progress" means and how it differs from "Ready for Review." You use AI, and you are still the data translator. This article shows how to build a Markdown map of your bases that Claude Code reads. Airtable stays the source of truth. The map tells Claude what the data means. ## Know what Claude cannot infer from Airtable Airtable structures your data. It does not explain the data to an outside AI. Without a map, Claude does not know: - which bases and tables you have; - which fields exist and what each one represents; - how the tables link; - what each status value means; - which records are active, archived, or priority; - the business logic behind the structure. Airtable's own AI features can write formulas and summarize a single record. In January 2026, they could not explain your whole data model to an outside AI. They could not answer questions across bases or help Claude write an update from your real pipeline. You need a context bridge. ## Choose the export route You are not building a live database connection. You are building a Markdown layer that teaches Claude how to read and reference your Airtable data. The route has five steps: 1. Export the base schemas: table structures, field types, and relationships. 2. Export the key record sets: active projects, priority items, and reference lists. 3. Store both as Markdown files in an Obsidian vault. 4. Write a `CLAUDE.md` that explains the data model. 5. Start Claude Code in the vault, so it reads the files. Airtable stays the source of truth, and the vault becomes Claude's map. You update the map by hand when the data changes in a way that matters. A live connection is also possible through the Airtable Web API or an MCP server. That route needs a scoped access token, read-only permissions, and a decision about which tables the agent may see. The export route needs no credentials, so start there. Read [what client data belongs in agent memory](/articles/client-data-in-ai-agent-memory) before you export client records into any shared folder. ## Export structure and context, not the whole database An Airtable base can hold thousands of records. Export the structure, plus the context Claude needs to reference the data: | Export | Contents | |---|---| | Base schemas | Table names, field definitions, relationships, views | | Active record sets | Current projects, open tasks, active clients | | Reference data | Status definitions, category lists, team assignments | | Priority items | The top 10 projects, urgent tasks, key deadlines | | Workflow rules | What moves a record between stages, and who owns each stage | The goal is context, not a copy of the database. ## Document each base schema The schema is the instruction manual. It tells Claude what data exists and how it is organized. For each base, record the table names and purposes, the field names and types, the linked-record relationships, and the key views with their filters. ``` --- base: Content Production purpose: Track blog posts from ideation to publication last-updated: 2026-01-28 --- # Content Production Base ## Tables ### Articles **Purpose:** Master list of all blog posts **Fields:** - Title (Single line text): Article headline - Status (Single select): Draft | In Review | Approved | Published - Author (Link to Contributors table) - Topic (Multiple select): SEO, AI, Productivity, Marketing - Target Keyword (Single line text) - Word Count (Number) - Publish Date (Date) - Performance (Link to Analytics table) **Key Views:** - Active Pipeline: Status = Draft or In Review - Ready to Publish: Status = Approved, Publish Date within 7 days - Top Performers: Sort by page views, filter Published ### Contributors **Purpose:** Authors and editors **Fields:** - Name (Single line text) - Role (Single select): Writer | Editor | Designer - Articles (Link to Articles table): All articles by this person - Email (Email) **Relationships:** - Articles.Author → Contributors.Name - Articles link back as Contributors.Articles ``` The schema teaches Claude the structure without one exported record. ## Export the active records For current work, export the state as a Markdown table. In Airtable, open a view filtered to the relevant records, such as Active Pipeline. Download it as CSV. Save the CSV in the vault and ask Claude Code to convert it to a Markdown table with a dated heading: ``` ## Active Articles (as of 2026-01-28) | Title | Status | Author | Topic | Keyword | Publish Date | |-------|--------|--------|-------|---------|--------------| | Claude Memory Guide | In Review | Writer A | AI | claude code memory | 2026-02-05 | | SEO Automation Tools | Draft | Writer B | SEO | seo automation | 2026-02-12 | | Productivity Systems | Approved | Writer C | Productivity | productivity system | 2026-02-01 | ``` Export what is active, not the full history. Update the file each week, or when priorities shift. The date in the heading tells Claude, and you, how fresh the data is. ## Define every status value Status values carry meaning. "Draft" and "In Review" describe different states, and Claude needs the difference. Write a reference file: ``` ## Article Status Definitions - **Draft**: Article in progress, not ready for review - **In Review**: Submitted to editor, awaiting feedback - **Approved**: Editor approved, scheduled for publication - **Published**: Live on site - **Archived**: Outdated or deprecated content **Workflow:** Draft → In Review (author submits) → Approved (editor approves) → Published (scheduled date reached) **Stuck signals:** - In Review for >5 days: editor bottleneck, check with the managing editor - Approved with no publish date: needs scheduling ``` The stuck signals let Claude spot problems, not only report states. ## Document the relationships Linked records are where Airtable earns its keep. Claude needs to know those connections: ``` ## Data Relationships **Articles → Contributors** - Each article has one author (Contributors.Name) - Each contributor can have many articles - Use this to check author workload or find articles by person **Articles → Analytics** - Each published article links to performance data - Use this to identify top performers or underperformers **Projects → Tasks** - Each project contains multiple tasks - Each task belongs to one project - Use this to track project completion percentage ``` With the relationships written down, Claude can answer "How many articles is Writer A working on?" without an explanation from you. ## Organize the vault folder Give the Airtable files one folder with three subfolders: ``` /Airtable/ /Schemas/ content-production-base.md client-projects-base.md hiring-pipeline-base.md /Active-Data/ active-articles.md current-projects.md open-positions.md /Reference/ status-definitions.md workflow-rules.md team-assignments.md ``` Schemas change rarely. Active data changes each week. Reference files change when the process changes. Keeping the three apart lets you update each on its own schedule. The [context manifest template](/articles/ai-context-manifest-template) shows how to record each file's owner, role, and load condition. ## Write the CLAUDE.md that indexes the bases `CLAUDE.md` tells Claude how to use the Airtable files. It holds a base index, the schema locations, the active data locations, the update schedule, and example questions with the file that answers each one: ``` ## Airtable Bases All Airtable schemas documented in `/Airtable/Schemas/`. Active data exports in `/Airtable/Active-Data/`. ### Content Production Base **Schema:** `/Airtable/Schemas/content-production-base.md` **Active data:** `/Airtable/Active-Data/active-articles.md` **Updated:** Weekly on Mondays **Purpose:** Track blog posts from draft to publication ### Client Projects Base **Schema:** `/Airtable/Schemas/client-projects-base.md` **Active data:** `/Airtable/Active-Data/current-projects.md` **Updated:** Daily **Purpose:** Manage client work, timelines, deliverables ### Common Queries - "What articles are in the pipeline?" → Read `/Active-Data/active-articles.md` - "How many projects are overdue?" → Check Current-Projects Status = Overdue - "Who's working on what?" → Reference Author or Assignee fields ``` The query examples teach Claude which file answers which question. Claude then reads [only the context the job needs](/articles/what-context-should-an-agent-read), not the whole folder. ## Worked example: five jobs before and after **Project update.** Before, you open Airtable, scan the projects, copy data into a document, and write the update. After, you ask Claude Code for this week's project update. It reads `current-projects.md` and lists completed items, work in progress, and upcoming deadlines. It drafts the update with real project names and statuses. **Pipeline bottleneck.** Before, you build filtered views, count records, and look for patterns by hand. After, you ask, "Where are we stuck?" Claude reads the active data and the status definitions. It finds five articles in review for more than five days and suggests a check on editor capacity. **Content calendar.** Before, you review Airtable, look for gaps, and try to recall the topic balance. After, you ask what to write next. Claude sees three SEO pieces and no AI pieces this month, checks the keyword targets, and suggests an AI topic. **Onboarding.** Before, you walk each new team member through every base and answer questions. After, the new hire asks Claude. It explains the tables, fields, workflow rules, and status meanings from the schema files. **Cross-base question.** Before, you open two bases in two tabs and connect the data by hand. After, you ask, "Which clients have content due this month?" Claude reads the client projects export and the content production export, links them, and answers. ## Keep the map current **Each week,** export the active record sets: current projects, articles in the pipeline, and open tasks. The export takes about 10 minutes. **Each month,** review the schema files. If you added fields or tables, update the schema file. **Each quarter,** audit the reference files. Confirm that the status definitions and workflow rules are still accurate. Most Airtable structure is stable. You update data, not schemas. The [plain-text memory article](/articles/plain-text-ai-memory) explains why a dated Markdown map stays readable after tools change. ## Know the limits of the export route This is not a live integration. Claude Code does not read Airtable directly or update records in real time. It is not a replacement for Airtable: your team still works there, and the vault is Claude's reference guide. It is not automatic sync: you export by hand when the data changes. The route is a context layer. Airtable holds the data. Claude gets the map it needs to understand and reference that data. If you have not used Claude Code or Obsidian before, both are simple to start. Claude Code installs with one terminal command, and Obsidian stores notes as plain Markdown files. ## Related: AI memory - [Export Google Workspace context to Markdown so Claude Code drafts from it](/articles/claude-code-with-google-workspace) - [Give Claude Code your HubSpot sales context through Markdown exports](/articles/claude-code-with-hubspot) - [Give Claude Code your Linear sprint and decision context in Markdown](/articles/claude-code-with-linear) ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```