> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getbased.health/llms.txt
> Use this file to discover all available pages before exploring further.
# AI chat for lab result interpretation
> Ask questions about your labs without pasting results manually. getbased sends the AI the relevant profile context when you chat.
The AI chat panel is a streaming conversation window built into getbased. It is also the main guided path for fresh profiles: after the first-visit tour, chat helps you decide what to add first and routes you to import, setup, or profile context only when needed. Every message you send automatically includes a snapshot of the current profile data.
## Open the chat
Click the **chat bubble** on desktop or the mobile chat button on smaller screens. On a fresh profile, the first-visit tour opens guided chat when it finishes. Returning desktop users with an empty profile may also see chat open automatically beside the welcome screen.
On desktop, the panel slides open beside the current view so charts, cards, and lenses remain usable while chat is open.
To expand the chat to full screen, click the **⛶** button in the chat header. Click it again to return to side-by-side mode. Your preference is saved between sessions.
Press **Escape** to close the panel.
If no AI provider is configured, the chat panel shows a setup guide instead of the conversation view. Click **Connect with OpenRouter** for one-click OAuth setup — no API key needed.
## What the AI knows
Every message includes the relevant context from your current profile. You never need to paste results into the chat.
| Context sent | Details |
| ----------------- | ----------------------------------------------------------------------------------------------------------------- |
| Lab results | All biomarker values across every draw date, with reference ranges and trend direction |
| Context cards | All nine lifestyle cards (diet, sleep, exercise, environment, and more) |
| Interpretive lens | Your chosen scientific paradigm or expert frameworks |
| Health goals | What you are working toward |
| Supplements | Full supplement list with date ranges |
| Change timeline | Timestamped log of card updates — the AI can correlate a diet change on March 1 with an LDL shift two weeks later |
| Wearables | Connected wearable metrics (heart rate variability, sleep scores, etc.) |
| DNA context | Relevant SNP data when you have a genome file loaded |
| Notes | Your freeform marker and profile notes |
| Cycle data | Menstrual phase context for female profiles |
## Current Focus
The **Current Focus** card appears on the dashboard and in the Insight lens. It shows a one-to-three sentence AI-generated insight drawn from your recent lab trends, health goals, wearable signals, and profile context. It gives you an orientation before you start typing and updates when your data changes.
Use Current Focus as a starting point. Click **Ask AI** next to a finding or open chat from any view to ask a follow-up about that specific marker or recommendation.
## AI personalities
The AI adapts its communication style based on the personality you choose. Switch personalities using the selector in the chat header.
A clear, evidence-informed tone. Explains markers plainly, notes trends, and flags concerns without drama.
A sharp, skeptical clinician who asks uncomfortable questions. Pushes back on assumptions and digs for root causes.
Type a name in the custom personality field and click **Generate**. getbased creates a draft style prompt with tone, reasoning preferences, and any perspective you asked for. You can edit the generated text before saving.
Custom personalities are saved per profile and persist across sessions. You can create a persona based on a specific medical philosophy, a fictional doctor character, or any style that makes conversations more useful for you.
The **Enforce evidence-based accuracy** toggle (off by default) adds a strict instruction to the AI to keep responses grounded in published research rather than speculation.
## Conversation threads
The chat panel has a **thread rail** listing past conversations. Each thread is named automatically from your first message, and you can rename any thread by clicking its name.
* Start a new conversation at any time with **New Chat**
* Switch between threads without losing history
* Up to **50 threads** per profile — oldest are pruned automatically
On mobile, tap the hamburger icon in the chat header to open the thread list.
Starting a new thread is the single biggest way to reduce token costs. History grows with every exchange — a fresh thread resets the context to just your lab data.
## Image attachments
Attach images to any chat message — photos of lab reports, supplement labels, food logs, or anything else you want the AI to see.
**Three ways to attach:**
Click the **paperclip** button in the chat input area and select a file.
Press **Ctrl+V** (or **Cmd+V** on Mac) to paste an image directly.
Drag an image file onto the chat input area.
Up to **5 images per message**. Supported formats: JPEG, PNG, GIF, WebP.
The **HD** button next to the paperclip toggles between standard (1024 px) and high-resolution (2048 px) quality. Standard mode is sufficient for most lab reports; use HD for fine print or dense tables.
Before sending, getbased analyzes each image and warns you if it detects blur, low light, overexposure, or low resolution — catching bad photos before they consume tokens.
All EXIF metadata (GPS location, camera model, timestamps, device serial numbers) is stripped from images before they leave your browser. Only pixel data reaches your AI provider.
The paperclip and HD buttons only appear when your active model supports vision (image input). If you don't see them, switch to a vision-capable model in **Settings → AI**.
## Web search
Toggle **Web** in the chat header to let the AI search the internet before responding. This is useful for questions about recent studies, drug interactions, or supplement research where up-to-date information matters.
Web search injects search results into the AI's context, significantly increasing input tokens. Expect messages to cost **2–4× more** than normal. The cost footnote shows a 🌐 indicator when search was active.
Web search is available with **OpenRouter**, **PPQ**, and **Venice**. The toggle is hidden when you are using other providers. If **PPQ Private TEE Mode** or **Venice E2EE** is active, web search is disabled so encrypted/private prompts are not sent into external search tooling.
## Stop and continue responses
While the AI is generating a response, a **Stop** button appears in the chat input area. Click it to halt generation mid-stream — useful when the AI is heading in the wrong direction and you want to rephrase your question.
After stopping, a **Continue** button appears below the partial response. Click it to resume generation from where the AI left off.
## Health context and AI features
Not everything you see in getbased is AI-generated. Understanding the distinction helps you trust the numbers.
### What the AI generates
* Chat responses and interpretations
* Current Focus insights
* Per-card health dots and tips
* Biology Score explanation text when you click **Explain this score**
* PDF lab import parsing
* Custom personality profiles
### What is deterministic (not AI)
| Feature | How it works |
| ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Reference ranges on charts | Directly from your lab report PDF or your own overrides — never generated by an LLM |
| Trend alerts ("dropped 25%") | Linear regression and slope thresholds in deterministic code |
| PhenoAge biological age | Levine 2018 closed-form formula over 9 biomarkers |
| Calculated markers (HOMA-IR, BUN/Creatinine, Free Water Deficit) | Published mathematical formulas |
| Biology Scores and Biological Coherence | Deterministic score engine over marker values, exact ranges, recency, coverage, and profile context; AI can explain the result but does not compute it |
| Channel doses in Light | Bird-Riordan spectrum reconstruction — reproducible photobiology math |
## Knowledge base grounding
If you have connected a knowledge base, the chat automatically retrieves the most relevant passages from your documents before each response. A badge in the chat header shows the active library name when this is running.
See [Connect a custom knowledge base](/guides/knowledge-base) for setup instructions.
## Token costs
Every message sends your full lab context plus conversation history. The chat header shows the name of your active model, and each AI response includes a footnote with the estimated token cost for that exchange.
| Component | Typical size |
| ---------------------------- | ------------------------------------------------------------ |
| System prompt | \~1,300 tokens |
| Lab context | 2,000–15,000 tokens (grows with draw dates and filled cards) |
| Conversation history | 0–10,000+ tokens (last 30 messages) |
| Image (current message only) | 1,000–5,000 tokens per image |
**Cost-saving tips:**
* Start new threads often — resetting history is the biggest lever
* Use standard image mode unless you need fine detail
* Run a local model via Ollama or LM Studio for unlimited free chat
* Venice offers free-tier models with no per-token charges