AI WITH A REVIEW QUEUE
AI that proposes. People who decide
Four attribute modes that run on any object. Every proposal waits for a person to accept it, every accepted value is tagged AI, and one workspace policy decides which models run and what data leaves.
Free plan, not a trial · Your data, your boundary · Government tenders across six markets 
AI attributes
A column that fills itself in
Add an AI attribute the way you add a text or formula field, on Companies, People, Deals or any object of your own. Pick the fields it may read, say what you want, and it runs across every record.
- Summarise the record
- one paragraph from the fields you tick, so a new teammate reads the account in a minute
- Answer a prompt
- a text, number or currency field filled from the record and your question
- Classify into an option
- a select value you can filter, group and report on, chosen from the fields it read
- Research on the web
- a field filled from what the web knows about the company, with the reason beside it
Change the prompt or the inputs and the column re-runs. Run it on records that need it and only the empty ones are touched.
The review queue
AI you approve before it writes anything
A mode runs and proposes a value for one record. The proposal waits in the queue with the record title, the field, and the exact value that accepting would write. Accept writes it, tagged AI so you can always tell it apart; Reject writes nothing.
- Default apply
- after review, or automatically for the fields you trust; either way the value stays tagged AI
- Data boundary
- one workspace setting decides what may leave for a model: the fields you declared, or record titles only
- Allowed models
- listed per workspace, so provider choice is one decision, not a per-feature surprise
Beyond attributes
Every number says how it got there
Scores, risk reads and briefs come with their reasons, so a wrong one is visible at once.
- Deal scores
- a score per open deal with a one-sentence reason
- Deal risk
- a read that names its factors: stage progress, recent activity, age, overdue items
- The coach
- a diagnosis, next steps each with a why and a timeframe, and the one question to ask next
- Write with AI
- a draft from the record and five rewrites in the composer, every one with Undo
- Prep briefs
- a one-minute brief per investor, built from profile facts and your own warm paths, part of matching
- Call insights
- summary, action items and risks from every recorded meeting, on the calls page
Frequently asked questions
Does the AI write to records on its own?
Only if you tell it to. By default every proposal waits in the review queue until a person accepts it. An admin can switch a field, or the workspace default, to apply automatically, and every value written that way still shows as AI.
What data leaves the workspace?
Only what the data boundary allows: the field values you ticked for an attribute, or record titles only. The target field never reads itself, and a daily credit limit keeps use inside what an admin set.
Which models does Ishara use?
Multiple providers, listed in the workspace policy. Every AI surface inherits the same list, so provider choice is a workspace decision.
Can I tell an AI value from a typed one?
Yes. Accepted values carry the AI tag, a filter separates them from anything a person typed, and a rejected proposal stays on the job so an empty field still explains why it is empty.
See exactly what it wants to write.
Add an AI attribute to any object and watch the review queue show you the value before it lands. Free is a standing plan, not a trial.
Free plan · 32,822 investors · six markets