Hire an AI research talk builder

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Claim-to-result and figure manifest
• Talk slides where rendered, speaker notes and rehearsal checks

How it does the job well

• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

Mistakes it avoids

• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.
• Over-generalising across places, periods or groups.

What a good result looks like

An example, not your task: Preparing an oral research presentation from completed work

• Claim-to-result list. Each claim in the paper, the table or figure behind it, the evidence offered and the gaps.
• Figure manifest. Talk-size figures with captions and data references, keeping uncertainty and missing observations.
• Slides. For each slide, its purpose, claim, evidence ID and visual, as an editable deck or LaTeX source if tools allow.
• Speaker notes and timing. Notes for each slide and an estimated time for each section, not a measured one.
• Check table. PASS, FAIL or NOT RUN for traceability, label size, kept limits and rehearsal.

How the work is checked

• Every important claim has a source or is marked as unverified.
• Disagreements between sources are named, not hidden.
• Limits and what to check next are listed.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Identify the defensible story. Read the supplied paper in full, including relevant appendices, with the source-note method. Record its claims, table/figure pointers, offered evidence and gaps. Map those notes to the attached result tables without assuming independent truth verification. Hand the approved source-bound claim list and exact evidence references to figure preparation.
• Prepare talk-size figures. Use your attached result tables and step 1's claim list to choose readable, faithful plots. The tables come from you; the claim list only decides which to plot. Preserve uncertainty, exclusions and missing observations. Hand figures, captions and data references to slide production.
• Build the timed talk. Use your compiled paper with step 1's evidence list and step 2's figures, plus audience and duration, to build the outline, supported slide formats and notes. Render only with available tools; return timing estimates and required rehearsal checks.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id prepare-a-source-checked-research-talk only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/prepare-a-source-checked-research-talk/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• PAPER: attach compiled paper and approved source text with citations.
• FIGURE_SOURCES: attach result tables, plotting code and approved assets with permissions.
• TALK_BRIEF: give audience, duration, format, required points and output format.
• RENDER_TOOLS: state available plotting, PowerPoint or LaTeX tools and confirmed conference rules.

Tools and access

• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.

Functions and deliverables

• Build a research talk from checked figures: Attach a paper, result tables and talk length. Get traceable figures, slides and speaker notes for review.
  • Claim-to-result and figure manifest
  • Talk slides where rendered, speaker notes and rehearsal checks
• Source note summariser: Paste an article, talk or chapter into this source note summariser. You get each claim, how well it is backed, the gaps and three quotes to keep.
  • Every claim with a quote and location, and the evidence behind each rated
  • The gaps and assumptions
  • What it adds to your question, three quotes to keep, and an 80-word summary
• Journal-ready figure maker: Give it your data. Get clear, honest, colour-safe figures with uncertainty shown, sized for journal export.
  • Charts with honest scales and visible uncertainty
  • Colour-safe palettes
  • Output sized for export
  • A record of every data transformation
  • A list of journal checks still to do
  Source: K-Dense.
• Conference talk slide maker: Turn your ML or systems paper into Beamer PDF and PowerPoint slides with timed speaker notes.
  • A Beamer PDF deck of your talk
  • An editable PowerPoint deck of the same slides
  • Speaker notes with timing and a line to lead into each next slide
  • A talk script you can read aloud (optional)
  Source: Orchestra Research.
• Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
  • A research folder with claims, methods and results
  • Every claim linked to its supporting table or log
  • Results tables copied with exact numbers
  • A record of dead ends and decisions
  • A short report on what was filled in and what was missing
  Source: Orchestra Research.

Tasks you can use it for

• Preparing an oral research presentation from completed work

Limits to check before starting

• You only want to know if your abstract matches your results: use Conference abstract evidence editor.
• You already have approved figures and only need slides: use the Conference talk slide maker.
• You need a poster, not a talk: use the Research poster maker.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the complete workflow or agent pack and unzip it.
• Give the complete folder to your AI. Start with START_HERE.txt, then provide the named inputs in the coordinator skill.
• Follow its checkpoints and check the evidence before using any output. Agent packs run one requested cycle; they do not create a schedule.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-source-checked-research-talk for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.