Inspect and curate the AI context
The AI generates its email drafts and recommendations from your context — the data you’ve maintained in Flino. To make sure the output fits you and your deal, it pays to look at what the AI currently “sees”. The AI context badge on the offer detail page is exactly for that.
Where to find the badge
Section titled “Where to find the badge”On the detail page of an offer there is a badge labelled “AI context: Well prepared” (or “Please improve” / “Missing fundamentals”, depending on the state). Clicking it opens the Inspect AI context sheet with the subtitle:
“This is the information Flino currently uses for follow-ups and AI suggestions.”
The badge tells you at a glance whether the AI has enough material right now or whether you should top it up.
The three levels
Section titled “The three levels”| Badge | Meaning |
|---|---|
| Well prepared | The AI has enough context for good suggestions. Tooltip: “The AI has enough context for good suggestions.” |
| Please improve | Enough for usable suggestions, but gaps slow down the quality |
| Missing fundamentals | Important basics are missing — suggestions become generic |
For “Please improve” and “Missing fundamentals”, the tooltip names the missing fields concretely: “For better AI suggestions, the following is missing: …”
What’s in the AI context sheet
Section titled “What’s in the AI context sheet”The sheet is split into sections — each shows a different source the AI can read from:
- Scope of work — the structured description of the offer. Edit it via the offer details (the “Scope of work” field).
- Important notes — notes you’ve marked as important (see prioritisation below).
- Call analyses — logged calls and their AI summary. Source: Log reactions.
- Objections and Reactions — what the customer said over other channels (WhatsApp, phone, …).
- Contact notes — notes you’ve stored on the contact itself. Edit them in the contact detail view.
- Last customer reply — the most recent reply from the email thread.
Per section you see whether the content is currently being used (badge “Used by AI”) or empty (e.g. “No important notes yet”).
At the top of the sheet there is also a summary with the derived keys: goal, interest, tone, last reply class (positive / question / objection / neutral / rejection), CTA, objection. So you see how Flino interprets the state of the conversation internally.
Prioritisation — what the AI should weight or ignore
Section titled “Prioritisation — what the AI should weight or ignore”Per entry in the sheet (note, reaction, reply) you can set the priority:
- Important — the AI weights this entry more heavily. Toast: “Marked as important”
- Standard — neutral weighting. Toast: “Set to standard”
- Ignore — the AI no longer uses this entry at all. Toast: “Excluded from AI context”
Useful when, for example, an old call is content-wise outdated and only adds noise to the output — set it to Ignore.
How the context is built
Section titled “How the context is built”The AI context is fed from several sources. The cleaner you maintain them, the better the suggestions:
- Incoming emails land in the activity timeline through the Gmail connection and become part of the context.
- Manually assigned emails from the Inbox join in too, as soon as you assign them to an offer.
- Reactions over other channels (phone, WhatsApp, SMS, LinkedIn) you record via the reaction dialogs. Call notes are taken in with their summary.
- Notes on the offer or contact are a direct field for free text.
- Scope of work and AI context description in the offer form provide structured sales arguments.
Recommendations for good AI results
Section titled “Recommendations for good AI results”- Capture all customer communication in Flino. Including the call where your customer half-confirmed the deal — log it as a “Call”, otherwise the AI can’t see it.
- Mark important notes as “Important”. Not all notes are equally relevant; flag explicitly what the AI should keep in mind.
- Set outdated information to “Ignore”. When the situation has changed, an old hint will otherwise block the recommendation.
- Fill scope and description. These fields are the basis for any personalised email. Without them, the AI generates generic text.
- Quickly inspect the context before important emails. A click on the badge takes seconds and can be the difference between “good suggestion” and “I have to rewrite it”.
Tip: nudges in the sheet
Section titled “Tip: nudges in the sheet”If something obvious is missing, the sheet shows small hints right next to the affected area — for example “Tip: A described scope of work clearly improves AI quality.” or “Tip: A call note improves follow-up quality.” Follow them — they come from the most common gaps.
Cross-links
Section titled “Cross-links”- React to replies — how incoming emails make it into the context
- Log reactions — capture off-channel reactions for the AI
- Inbox — pull scattered emails in via a Gmail label
- AI writing style — how you steer the tone applied on top of the context
- Intelligent recommendations — the context also feeds the recommendation engine