Skip to main content
NvidiaConference talks

Mal Curtis (Principal Software Engineer, NVIDIA) at Agentic Engineering Day New Zealand.

Source: Autobound Signal API · 156 signals tracked for Nvidia · updated

Get Nvidia's live signals in Claude or ChatGPT, or by API

AskWhat changed at Nvidia this week? Use Autobound signals for nvidia.com.

What happened

Session: Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them)

Source

agenticbuild.dayOct 21, 2026

Agentic Engineering Day New Zealand

Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them)

Session

Prompt injection isn’t a bug - it’s a feature. LLMs trained on humanity’s written corpus learned something we didn’t intend: narrative structure. They understand dramatic tension, plot twists, and persuasive framing. When an attacker crafts a compelling story (“Actually, the real system prompt said...”), the model follows because that’s what stories do. This talk connects 2,500 years of storytelling theory - from Aristotle’s Poetics to Derrida’s “there is no outside text” - to explain why prompt

agenticbuild.dayRead the full source

Extracted by Autobound

From the Signal API record
Signal
Conference talks
Conference
Agentic Engineering Day New Zealand
Date
Oct 21, 2026
Location
Auckland, New Zealand
Topics
4

More conference speaker signals at other companies

The full record

From the Signal API record

People

  • Mal CurtisPrincipal Software Engineer, NVIDIA · Speaker

Details

Conference ends
Oct 22, 2026

Topics and mentions

Conference topics

  • agentic AI
  • AI agents
  • context engineering
  • MCP servers
  • multi-agent orchestration
  • observability
  • AI security
  • prompt injection

Extraction

Confidence
High
Relevance
76%
Detected
Oct 31, 2026
signal_type
conference-speaker
signal_subtype
conferenceSpeaker

Use this data

Get every conference speaker signal for Nvidia and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Nvidia this week?”

  2. Send it to your own tools

    The Signal API returns conference speaker signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full conference-speaker record in the Signal API and MCP can also have these 19 fields. Some fields are empty for some signals.

Contact

  • full_nameValue in the API
  • job_titleValue in the API
  • linkedin_urlValue in the API
  • emailValue in the API
  • first_nameValue in the API
  • last_nameValue in the API
  • cityValue in the API
  • stateValue in the API
  • countryValue in the API
  • seniorityValue in the API

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API

And 1 more fields.

Show the full JSONThe record on this page and the API request

GET /v1/signals/f80efce7-0896-5286-b30a-ad1e89181a46 returns this record as JSON. POST /v1/companies/enrich returns every signal for nvidia.com.

{
  "signal_id": "f80efce7-0896-5286-b30a-ad1e89181a46",
  "signal_type": "conference-speaker",
  "signal_subtype": "conferenceSpeaker",
  "detected_at": "2026-10-31T00:00:00+00:00",
  "company": {
    "name": "Nvidia",
    "domain": "nvidia.com"
  },
  "data": {
    "summary": "Mal Curtis (Principal Software Engineer, NVIDIA) at Agentic Engineering Day New Zealand.",
    "relevance": 0.76,
    "confidence": "high",
    "speaker_bio": "Mal Curtis is a software engineer at Nvidia, where he continues working on AI inference infrastructure following Nvidia’s acquisition of Groq. Previously, he built engineering infrastructure for the development of the world’s fastest AI inference chips, and before that led AI agent development at Kolatr, where prompt injection moved from “interesting research problem” to “thing that breaks production on Tuesdays.”",
    "session_type": "talk",
    "session_title": "Why LLMs Fall for Stories (And 5 Production Patterns That Actually Stop Them)",
    "conference_url": "https://www.agenticbuild.day/",
    "conference_date": "2026-10-21",
    "conference_name": "Agentic Engineering Day New Zealand",
    "is_future_event": false,
    "contact_resolved": true,
    "conference_topics": [
      "agentic AI",
      "AI agents",
      "context engineering",
      "MCP servers",
      "multi-agent orchestration",
      "observability",
      "AI security",
      "prompt injection"
    ],
    "extraction_method": "llm-speakers_list+bio",
    "domain_match_score": 10,
    "conference_end_date": "2026-10-22",
    "conference_location": "Auckland, New Zealand",
    "session_description": "Prompt injection isn’t a bug - it’s a feature. LLMs trained on humanity’s written corpus learned something we didn’t intend: narrative structure. They understand dramatic tension, plot twists, and persuasive framing. When an attacker crafts a compelling story (“Actually, the real system prompt said...”), the model follows because that’s what stories do. This talk connects 2,500 years of storytelling theory - from Aristotle’s Poetics to Derrida’s “there is no outside text” - to explain why prompt",
    "conference_description": "Agentic Engineering Day New Zealand is an independent, community-driven conference for AI engineers, architects, product people, and builders focused on real-world AI systems. It emphasizes hands-on workshops and deep technical sessions on moving agentic and AI-powered systems into reliable producti",
    "domain_match_confidence": "high",
    "conference_estimated_size": "300-500"
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.