公式動画ピックアップ
AAPL
ADBE
ADSK
AIG
AMGN
AMZN
BABA
BAC
BL
BOX
C
CHGG
CLDR
COKE
COUP
CRM
CROX
DDOG
DELL
DIS
DOCU
DOMO
ESTC
F
FIVN
GILD
GRUB
GS
GSK
H
HD
HON
HPE
HSBC
IBM
INST
INTC
INTU
IRBT
JCOM
JNJ
JPM
LLY
LMT
M
MA
MCD
MDB
MGM
MMM
MSFT
MSI
NCR
NEM
NEWR
NFLX
NKE
NOW
NTNX
NVDA
NYT
OKTA
ORCL
PD
PG
PLAN
PS
RHT
RNG
SAP
SBUX
SHOP
SMAR
SPLK
SQ
TDOC
TEAM
TSLA
TWOU
TWTR
TXN
UA
UAL
UL
UTX
V
VEEV
VZ
WDAY
WFC
WK
WMT
WORK
YELP
ZEN
ZM
ZS
ZUO
公式動画＆関連する動画 [AI Agents in Production: What It Actually Takes | MongoDB.local NYC 2026]
Subscribe to the MongoDB for Developers YouTube Channel: https://www.youtube.com/@MongoDBDevelopers?sub_confirmation=1
Explore MongoDB Atlas Agent Engine: https://www.mongodb.com/products/platform/atlas-agent-engine
AI agent demos are easy to build. Making agents dependable in production takes more: durable execution, verification, observability, cost-aware model routing, and security controls that work across tools and workflows.
Recorded at MongoDB.local NYC 2026, moderator Sophia Dew of MTS Live is joined by Maxim Fateev (Co-founder and CTO, Temporal), Louis Vichy (Co-founder, OpenRouter), and Walden Yan (Co-founder and CPO, Cognition). The panel explores what it takes to run AI agents at scale, including recovery from failures, software testing and evaluation, model selection and cost, sandboxing and access controls, centralized guardrails, human oversight, and the next frontier of operating software built by AI.
Chapters
00:00 Welcome: What does production AI take?
00:53 Why productionizing agents is an organizational challenge
02:06 Enterprise control planes, governance, and visibility
04:16 Why agents need to test and verify their work
06:12 Model routing, evaluations, and agent costs
09:50 Durable execution for long-running agents
12:23 Guardrails for agent-generated code and actions
13:28 Secrets, sandboxing, and agent security
16:01 Tracking network calls, credentials, and permissions
20:40 Centralized guardrails and the limits of human approvals
24:11 New frontiers: agents for security work
26:22 Agents beyond engineering: finance, GTM, and support
28:00 The next frontier: operating AI-generated software
29:11 Open models, self-hosting, and enterprise tradeoffs
31:42 What will still be unsolved next year?
33:03 Outcome-driven agents and organizational politics
34:01 Closing remarks
#AI #AIagents #MongoDB
Visit Mongodb.com → https://mdb.link/MongoDB
Read the MongoDB Blog → https://mdb.link/Blog
Read the Developer Blog → https://mdb.link/developerblog
MongoDB for Developers YouTube Channel → https://www.youtube.com/@MongoDBDevelopers
568
1