> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.rightbrain.ai/v-1/docs/patterns/tools/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.rightbrain.ai/_mcp/server.

# Internal AI Tools

> Build versioned AI tools for internal teams and deliver them through existing systems.

Use a Rightbrain [Task](/docs/concepts/tasks) for one bounded internal operation, or an [agent](/docs/concepts/agents) when the work requires runtime decisions, multiple tools, or conversation state. Deliver the same versioned capability through your API, triggers, or [Connections](/docs/concepts/connections) to the systems where the team already works.

## Why Tasks Work for Internal Tools

* **Stable contract** - Typed input and output keep downstream workflow code predictable.
* **Reusable execution** - The same Task can serve direct API calls, webhook-triggered work, and agent tool calls.
* **Controlled context** - Use [Skills](/docs/concepts/skills) for reusable procedures and [Collections](/docs/concepts/collections) for retrieved source material.
* **Safe iteration** - Revisions, evals, and rollback separate configuration changes from release decisions.

## Common Internal Tool Patterns

#### Document Intelligence

#### Invoice Processing

**Input:** PDF or image upload\
**Output:** Structured JSON with vendor, items, amounts, and dates\
**Used by:** Finance teams for monthly close and AP automation

#### Contract Review

**Input:** Contract PDF\
**Output:** Structured summary highlighting key terms, obligations, risks, and deadlines\
**Used by:** Legal and procurement teams

#### Resume Screening

**Input:** Resume file (PDF, DOCX, etc.)\
**Output:** Scored candidate profile with extracted skills, experience, education, and match reasoning\
**Used by:** Recruitment teams for initial candidate screening

#### Expense Report Parser

**Input:** Photo or PDF of receipt\
**Output:** Expense entry with extracted category, amount, and compliance status\
**Used by:** Employees and finance teams for expense submissions

#### Content Generation

#### Meeting Summariser

**Input:** Meeting transcript or recording\
**Output:** Action items, decisions, and key discussion points\
**Used by:** All teams for post-meeting follow-ups

#### Knowledge Article Generator

**Input:** Internal chat logs or support tickets\
**Output:** Drafted FAQ or knowledge base article\
**Used by:** Customer support and operations teams

#### Brand Compliance Reviewer

**Input:** Draft content such as blog posts, product copy, or internal announcements\
**Output:** Feedback summary highlighting tone, phrasing, and style deviations\
**Used by:** Marketing, communs, and product teams

#### Outreach Copy Generator

**Input:** Prospect details or CRM notes\
**Output:** Personalised outreach message or email draft\
**Used by:** Sales and marketing teams for tailored communication

#### Classification & Routing

#### Support Ticket Classifier

**Input:** Incoming ticket text\
**Output:** Category, urgency, and suggested resolver group\
**Used by:** Support and triage teams

#### Lead Qualification Scorer

**Input:** CRM lead details and engagement history\
**Output:** Qualification score with next-step recommendation\
**Used by:** Sales and marketing operations

#### Inbound Request Router

**Input:** Form submission or email content\
**Output:** Department or team assignment with priority tag\
**Used by:** Operations and support teams to route incoming requests efficiently

#### Document Type Classifier

**Input:** Uploaded document or PDF\
**Output:** Document category (e.g., invoice, contract, policy) and handling instructions\
**Used by:** Finance, legal, and compliance teams for automated document sorting

#### Analysis & Insights

#### KPI Summariser

**Input:** Uploaded CSV or API data feed\
**Output:** Summary of key metrics and anomalies\
**Used by:** Department heads and analysts

#### Code Review Assistant

**Input:** Pull request diff\
**Output:** Potential issues, style violations, and improvement suggestions\
**Used by:** Engineering teams

#### Trend Analysis Reporter

**Input:** Historical performance data or analytics export\
**Output:** Narrative summary of trends, shifts, and contributing factors\
**Used by:** Strategy and analytics teams for periodic reporting

#### Customer Feedback Synthesiser

**Input:** Survey responses or support feedback logs\
**Output:** Thematic breakdown with sentiment insights and improvement areas\
**Used by:** Product and customer experience teams

## Real-World Example: Legal Team Contract Analyser

**The Challenge**: Legal team reviewing 50+ vendor contracts monthly, each taking 45+ minutes to analyse for key terms, risks, and non-standard clauses.

**Task Configuration**:

* **Input**: Contract PDF upload
* **Context**: Company's standard terms, red flag clauses, approval thresholds
* **Output**: Structured JSON with:
  * Contract type and parties
  * Payment terms and amounts
  * Key obligations for both sides
  * Identified risks with severity
  * Non-standard clauses highlighted
  * Recommended approval level

**Deployment**:

* Primary: Slack bot in #legal-contracts channel
* Secondary: API integration with contract management system
* Fallback: Direct API execution for ad-hoc reviews

**How Legal Team Uses It**:

1. Procurement drops contract in Slack
2. Legal team member clicks "Analyse Contract"
3. Task returns structured analysis in \~30 seconds
4. Team reviews flagged items, approves or requests changes
5. Analysis automatically logged in contract system

**Why It Works**:

* **Configurable**: Updated monthly as approval policies change
* **Predictable**: Always returns same structured format for downstream logging
* **Stateless**: Each contract analysed independently, no cross-contamination
* **Composable**: Same Task used in Slack and contract system API

## Real-World Example: Sales-Call Deal Intelligence

**The Challenge**: Reps finish discovery calls with an hour of recording and no time to write it up, so budget, authority, and timeline detail get lost.

**Task Configuration**:

* **Input**: Call recording (WAV, MP3, and other common formats)
* **Processing**: An audio-transcription input processor turns the recording into text before the reasoning model sees it — the audio itself never reaches your analysis model
* **Output**: Structured JSON with the full BANT breakdown — budget, decision-makers, timeline, and the pain points named on the call

**How It Runs**:

One model transcribes the audio and a second reasons over the transcript, so you can pair the best transcription with the best analysis. On a real discovery call the transcription took about 10.8 seconds and the analysis about 35 seconds, extracting the budget, the named decision-makers, and an end-of-quarter timeline into a record your CRM can ingest directly.

> **Note**
>
> The best internal tools are the ones your team actually uses. Start with one painful, repetitive task. Build a focused tool. Make it work well. Then expand to more use cases as teams see the value.

## Next Steps

#### [Build Your First Tool](/docs/quickstart/create-a-task)

Create a task for your team's specific needs

#### [Connections & MCP](/docs/concepts/connections)

Deploy to Slack, API, MCP, or webhooks

#### [Skills](/docs/concepts/skills)

Package team procedures and domain guidance for reuse

#### [Input processors](/docs/concepts/input-processors)

Transform documents, audio, URLs, and search input before a Task runs

#### [Collections](/docs/concepts/collections)

Ground internal tools in controlled source material

> Build reliable AI agents that run inside your existing tools and workflows. Rightbrain developer documentation.