Tables New
Give your AI a database that remembers
Structured records your AI client creates, reads and updates through FloConnector: a lead list, a content calendar, a job log. They stay put between chats, and you can edit every row in the dashboard.
Before
Your AI finds things. Then it forgets them.
A chat is a scratchpad. The moment you want a list that lasts, a lead tracker or a job log, there is nowhere for it to go.
-
Every chat starts from zero
The list your AI built on Monday is gone by Tuesday. You paste it back in, or you start again and hope it finds the same things.
-
A spreadsheet can't push back
A model writing to a sheet has to keep the grid in shape itself. Text lands in a number column, a header gets overwritten, and nothing says no.
-
Retries make duplicates
Models retry when a call is slow. With nothing to match on, the same lead lands twice, then three times, and the totals quietly drift.
How it works
Three sentences, and it's set up
You never design a schema or open a form. Say what to keep track of and your AI makes the table, fills it from the tools you already use, and reads it back in any chat after.
- 1
You ask for a list, in plain English flc_table_create 4 fields · key: email - 2 It reads your tools and writes the records flc_record_upsert 4 records · 0 duplicates
- 3 Any chat after finds them again flc_record_query 2 quoted · $12,700
The conversation - Keep a list of everyone who asked for a quote this week, with their budget.
- Done. I've made a table called Quote requests with email, company, budget and stage, keyed on email, and added the 4 I found.
- A week later, a new chat
- What's still quoted, and what's it worth?
- Two: Northwind and Boltworks, $12,700 between them.
Fill it from your tools
Your AI reads your tools and writes it down
Point it at your inbox, your booking page and your forms. It reads each through its connector, matches what it finds on the key, and writes the lot to one table. Next time, it reads the table instead of the inbox.
- Matched on a key you choose, so one person is one record
- Up to 500 records a write, and none land if one is wrong
- Ask it on a schedule and the table keeps itself current
- records per write
- 500
- key to match on
- 1
- duplicates on a retry
- 0
- per table call
- $0
Built for a model to write to
A model can't make a mess of it
Models retry, repeat themselves and guess. Every rule below exists so that none of that ends up in your data.
-
All or nothing
Up to 500 records in one write, every one validated first. If any is wrong, nothing lands and the error names each one, so a retry never makes duplicates.
-
A key that upserts
Name a field as the key, an email or an invoice number, and writes match on it regardless of case. One record per lead, however often it comes up.
-
Numbers that stay put
Records are numbered 1, 2, 3 and a number is never reused. "Record 12" written into a note still means the same record next month.
-
Typed fields
Eleven types, from text and numbers to dates, options, emails and links. A value that doesn't fit is refused with the reason, never guessed at.
-
No silent overwrites
Every record carries a version. Your AI can ask for a write to be refused if someone changed the record since it last looked.
-
Totals across your tools
Load a whole table into a temporary, in-memory analytics workspace and query it with SQL, joined against data from your connectors.
In the dashboard
Every row is yours to see and edit
Tables sit in your workspace beside your connectors and skills. Open one and it's a grid you can work in, with the same records your AI reads.
- Sort, filter and search on any field
- Fix a cell, add a field, reorder the columns
- Export any table to CSV, whenever you like
- Owners and admins see tables; a custom role can open them to members
Ten tools
On the FloConnector connector
Tables live on the FloConnector connector, next to skills. Switch it on for a profile and your AI gets all ten. Every tool acts as you, with the permissions your role gives you.
Create your first tableflc_table_* · flc_record_*
10 tools · $0 a call- flc_table_list Every table, its record count and fields, and the plan's room
- flc_table_describe One table's fields, types, key and two example records
- flc_table_create A new table with typed fields and an optional key
- flc_table_update Rename, add, change, remove or reorder fields
- flc_table_archive Archive a table, or restore it
- flc_record_query Filter, sort, search, count and page records
- flc_record_insert Add up to 500 records at once
- flc_record_upsert Add or update up to 500, matched on the key
- flc_record_update Change fields on records by number
- flc_record_delete Delete records by number
Room on every plan
Limits that never delete
Per workspace, across all its tables. A write that would pass a limit is refused and tells your AI how much room is left. Downgrade, and nothing is deleted: the workspace goes read-only until it is back under.
Questions
What is a table in FloConnector?
A table is a set of records your AI client keeps in your workspace: a lead list, a content calendar, a job log. Your AI creates and writes to it through the FloConnector connector, it stays put between chats, and you can see and edit every row in the dashboard.
How is this different from a spreadsheet connector?
A spreadsheet is a grid of cells a model has to keep in shape itself. A table has typed fields, a unique key and all or nothing writes, so a model can't put text in a number column, add the same lead twice, or leave a batch half written.
Who can see my tables?
Owners and admins of the workspace. Members see none by default, because tables can hold sensitive data and a new teammate joins as a member. A custom role can give members read or write access.
Do table tools cost anything per call?
No. Table tools work on FloConnector's own data, not a vendor's API, so they are included like the rest of FloConnector's own tools. You only pay for calls that reach a connected platform.
What happens if I go over my plan's limits?
Nothing is deleted, ever. A write that would pass a limit is refused and says how much room is left. A workspace that is over a limit after a downgrade becomes read-only until it is back under: you can still view, export and delete.
Can I get my data out?
Yes. Every table exports to CSV from the dashboard, and your AI can read every record through the connector at any time.
Is it ready to use?
Tables is an early release, marked Alpha in the dashboard. It works and is safe to use; how tables are structured may still change as we learn from real workspaces.
Start keeping track
Your first table takes one sentence.
Connect FloConnector to Claude, switch on the FloConnector connector for a profile, and ask it to start a list. Tables are included on every plan.