Matthew Berman Demonstrates ChatGPT Connectors and Deep Research

In a 2025 demonstration, connected services supply information for a natural-language question about recent HubSpot deals.

MBMatthew BermanVortrag · Forward Future
Kanal
Matthew Berman
Veröffentlicht
6. Juni 2025
Video
0:54
Lesezeit
1 Min.
Folien
2
Original
Englisch
Auf YouTube öffnen
Beim Scrollen schrumpft das Video in die rechte untere Ecke und läuft weiter. Untertitel folgen Ihrer Lesesprache.
LesespracheIn 2 Sprachen verfügbar
Diesen Artikel gibt es noch nicht auf Deutsch, daher wird das Original (Englisch) angezeigt.
ZUSAMMENFASSUNG

In 30 Sekunden

In June 2025, Matthew Berman introduces ChatGPT connectors and demonstrates selecting connected sources in deep research. He asks about recently closed deals, clarifies that he means HubSpot, and shows a generated table. The video illustrates that session’s workflow; product availability and interface details can change.

  1. 1Connecting servicesBerman introduces connectors for services including Gmail, Box, calendars, HubSpot and GitHub, as described at the time.
  2. 2Choosing sourcesHe selects deep research and describes a menu for enabling or disabling connected services.
  3. 3A HubSpot questionAfter a clarification, the system queries HubSpot and presents a table of deals closed in the preceding 30 days.

Das Wichtigste

  1. The 2025 demonstration connects ChatGPT to external services as sources for research.
  2. Berman shows the deep research interface for toggling connected sources.
  3. When asked about closed deals, ChatGPT first asks which source to search.
  4. The demonstrated HubSpot query produces a formatted table, although the clip does not independently verify its completeness.
VOLLTEXT

Den bearbeiteten Text nach Kapiteln lesen

Nur das Transkript
01

Connecting services to ChatGPT

Berman introduces connectors and names services that can supply information. He shows how to enable sources for deep research in the 2025 interface.

OpenAI has introduced connectors that let ChatGPT work with information from services you connect. I mention Gmail, Box, calendars, HubSpot, Outlook, GitHub, Teams and Linear, with more services expected. This demonstration reflects the product as shown in June 2025; the available integrations and interface may change.

Selecting deep research
FOLIE 1 / 2Selecting deep researchThe 2025 interface shows deep research selected in the composer.

In the interface shown, I select Tools and run deep research, then use a dropdown to turn connected sources on or off. That means I can ask questions about information in a connected service, such as email, instead of looking through it manually.

02

Querying recent deals

A request for deals prompts ChatGPT to ask which source to use. After Berman specifies HubSpot, the demonstration shows a query and a formatted table.

Clarifying the source
FOLIE 2 / 2Clarifying the sourceChatGPT asks where to search for recent deals before the presenter specifies HubSpot.

For the demonstration, I ask which deals closed in the last 30 days. ChatGPT asks where to look, and I specify HubSpot. It then shows Python analysis and queries against HubSpot before producing a formatted table of closed deals. The clip shows the result, though it does not independently verify that the table is complete.

Mehr aus diesem Kanal

12 Folien34:21EN
MBMatthew Berman· 27. Okt. 2026Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.AnthropicAI SafetyEnterprise-KI+2
6 Folien25:50EN
MBMatthew Berman· 24. Okt. 2026Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.Open-weight modelsBenchmarksAI cost & performance+1
2 Folien32:20EN
MBMatthew Berman· 23. Okt. 2026Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.Local inferenceOpen-weight modelsAI cost & performance+1
6 Folien1:03:37EN
MBMatthew Berman· 23. Okt. 2026Matthew Berman’s Team Tests Kimi K3.1 on Animation, Games, and ChartsMatthew Berman, Alex, Brian · Forward FutureA live team AMA turns into an informal test of Kimi K3.1, from personal-agent workflows to motion graphics, a browser game, and a benchmark chart.Coding-AgentenGenerative mediaEvals+2
0:53EN
MBMatthew Berman· 22. Okt. 2026Sam Altman on AI and the Discovery of New KnowledgeSam Altman · OpenAIAltman expects progress in mathematical discovery to extend to biology, materials and energy.AI for scienceMathematicsComputational Biology+1
Folien0:22EN
MBMatthew Berman· 21. Okt. 2026A Robot Bodyguard Video Shows Dramatic Rescue ScenariosMatthew Berman · Forward FutureMatthew Berman reacts to a short robot demonstration depicting fighting and vehicle-rescue scenarios.RoboticsEvals