CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

ainativedev/aidevcon-2026-nyc

AI Native DevCon 2026 New York — practical agent skills grounded in conference talks

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

outline.mdskills/talk-boeckeler-context-lifecycles/references/

Talk navigation

Talk: Context != Context: One Window, Different Lifecycles
Speaker: Birgitta Boeckeler
Event: AI Native DevCon New York 2026
Recording: https://www.youtube.com/watch?v=NxypyNu1944

This index paraphrases the supplied corrected SRT. The accompanying transcript retains its original cue numbers, full start/end timestamps, and spoken wording, with subtitle line wrapping joined. Cues 195–205 contain an inserted conference promotion and are omitted. The unchanged timing allows references to the supplied recording.

TopicTimestampCues
Why one context window contains semantically different material00:27–02:188–38
Codified and ambient context: authorship, reuse, rate of change02:20–04:5139–76
Complementary review rules and incident history04:52–05:5177–91
Task phase and repository context; onboarding example05:53–07:2092–111
Codified loop attributed to Patrick Debois07:21–08:12112–123
Clarity, actionability, fidelity, efficiency, security08:33–09:54129–148
MCP delivery: who handles quality, permissions, recall and precision?09:56–11:19149–170
Context engine and task-time reasoning11:20–12:37171–189
Ambient loop: ingest and assemble replace generate and distribute12:38–12:59190–194
Promotional interlude omitted13:00–13:37195–205
Ingest: synchronization, freshness, permission models, identity13:41–16:00206–240
Evaluate: scenarios, gold documents/answers, conflict and absence16:02–17:29241–260
Assemble: caller needs, depth, latency and cost17:33–18:57261–282
Conflict example and code as a source of reality18:59–20:41283–306
Observe: disputed sources, engine bias, downvoted-answer analysis20:43–22:45307–336
Diverse implementations; memory, generated wikis, selective indexing22:48–24:53337–365
Put stable instructions and changing facts in suitable places24:55–25:39366–376
Maintain input knowledge, access and recurring conflicts25:41–28:31377–422
Agent-authored context and possible feedback problems28:33–30:03423–443

Short quotations

Read surrounding cues before using a quote as evidence.

  • Cue 77, 04:52: "And they complement each other."
  • Cue 193, 12:51: "I would call it ingest here. And the distribute step I would call assemble."
  • Cue 300, 20:08: "we have the code as our let's not say source of truth, but source of reality."
  • Cue 363, 24:41: "single conversation. Not every conversation on Slack is knowledge,"
  • Cue 401, 27:09: "We have to write things down. Think out loud."

Source limits and attribution

The transcript includes speech artifacts, fragments, and references to slides that are not bundled. The author names and article title around 08:44 are garbled; do not invent the exact citation. The identity example around 15:51–16:00 is also garbled; use the clear explanation in cues 230–237 instead. The suspected-conflict sample and percentages are approximate, and the transcript provides neither raw observations nor independent accuracy measurements. Discussion of Unblocked describes the presentation's context; current capabilities need separate verification. There is no reliable indication that every passage mentioning a product is a general technical prescription.

skills

talk-boeckeler-context-lifecycles

tile.json