| We have Gemma-4, Kimmi K2.6 and Opus-4.7 now on the @vectara hallucination leaderboard.
@Google Gemma-4 is surprising g… |
@vectara |
Company |
Original |
2026-04-21 |
259 |
6 |
1 |
0 |
0 |
1 |
| Some new case studies added to awesome-agent-failures, including the @amazon-Q Retail outage, the @ClaudeCode Terraform… |
@vectara |
Company |
Original |
2026-03-23 |
371 |
4 |
0 |
0 |
0 |
0 |
| More case studies for agentic failures added to the "awesome-agent-failures" repository
Check them out: HHS Chatbot, Am… |
@vectara |
Company |
Original |
2026-02-20 |
307 |
5 |
1 |
0 |
1 |
1 |
| Lots of new LLM releases from China - we just updated @vectara's hallucination leaderboard with evaluations for @Zai_or… |
@vectara |
Company |
Original |
2026-02-17 |
645 |
9 |
1 |
0 |
1 |
1 |
| Building AI agents on-prem?
Our latest blog breaks down how to architect **robust on-prem AI agent orchestration**—fro… |
@vectara |
Company |
Original |
2026-02-09 |
206 |
5 |
1 |
0 |
0 |
0 |
| New additions to Awesome Agent Failures: 3 fresh case studies.
The most interesting one? You already know.
moltbook/op… |
@vectara |
Company |
Original |
2026-02-02 |
208 |
4 |
0 |
0 |
1 |
1 |
| 📢 Calling all AI enthusiasts!
Join AI by Hand ✍️ Seminar: Foundation (AI Eval): a free live Zoom seminar diving into f… |
@vectara |
Company |
Original |
2026-01-27 |
171 |
5 |
0 |
0 |
0 |
0 |
| Context engineering depends on precision, and precision depends on retrieval.
This is why Vectara was built on a simpl… |
@vectara |
Company |
Original |
2026-01-14 |
156 |
4 |
1 |
0 |
0 |
0 |
| Three new case studies of agent failures added to Awesome-Agent-Failures repo, including the so called "LangGrinch" vul… |
@vectara |
Company |
Original |
2026-01-07 |
191 |
10 |
2 |
0 |
1 |
0 |
| In a recent Digital IT News piece on AI predictions for the year ahead, @EvaNahari explains why AI agents will require … |
@vectara |
Company |
Original |
2026-01-05 |
220 |
10 |
2 |
0 |
2 |
0 |
| As the year comes to an end, it’s a good moment to pause and look at where enterprise AI is actually heading.
We share… |
@vectara |
Company |
Original |
2025-12-29 |
250 |
12 |
2 |
0 |
2 |
0 |
| We've create this app to test your knowledge about agentic AI, just in time for the holidays.
https://t.co/9YKjwghToe … |
@vectara |
Company |
Original |
2025-12-18 |
253 |
9 |
1 |
0 |
0 |
0 |
| ICYMI: we've recently released a ton of new features for developing agents with @vectara - e.g. subagents and artifacts… |
@vectara |
Company |
Original |
2025-12-18 |
222 |
9 |
1 |
1 |
0 |
0 |
| A key design goal of Open-RAG-Eval was to allow reference-free evaluation of both retrieval (using the UMBRELA score) a… |
@vectara |
Company |
Original |
2025-12-16 |
216 |
8 |
3 |
0 |
0 |
1 |
| When AI agents look impressive in demos but struggle in real workflows
A recent article on Microsoft Copilot highlight… |
@vectara |
Company |
Original |
2025-12-15 |
248 |
11 |
4 |
0 |
0 |
2 |
| We’re sharing a deeper look at how the Tool Validator Guardian Agent works and why tool-call reliability is critical fo… |
@vectara |
Company |
Original |
2025-12-12 |
465 |
12 |
4 |
1 |
0 |
1 |
| We’re excited to introduce the Tool Validator, our new Guardian Agent that reviews an agent’s workflow plan before exec… |
@vectara |
Company |
Original |
2025-12-11 |
194 |
12 |
3 |
0 |
1 |
1 |
| OODA announced OODA AI, a new intelligence tool built on vetted research and supported by Vectara’s retrieval and gener… |
@vectara |
Company |
Original |
2025-12-10 |
686 |
16 |
5 |
0 |
1 |
0 |
| Here are 5 reasons to use an Agentic Operating System instead of building AI Agents with DIY tools.
https://t.co/MskeK7… |
@vectara |
Company |
Original |
2025-12-09 |
218 |
8 |
1 |
0 |
2 |
0 |
| As AI Agents grow in usage, evidence is starting to pile up about the risks from agents without governance.
ICYMI: we … |
@vectara |
Company |
Original |
2025-12-08 |
139 |
8 |
2 |
0 |
1 |
0 |
| Google Antigravity vibe-codes user's entire drive out of existence.
https://t.co/w8rJUvh6v3
We just added this as a ca… |
@vectara |
Company |
Original |
2025-12-05 |
350 |
9 |
3 |
1 |
0 |
0 |
| Sub Agents are now available in Vectara’s Agent OS, making it easier to build complex multi-agent workflows that stay a… |
@vectara |
Company |
Original |
2025-12-04 |
326 |
9 |
4 |
0 |
0 |
1 |
| We just released Artifacts for Vectara Agents, giving agents the ability to work directly with files in a session. They… |
@vectara |
Company |
Original |
2025-12-01 |
396 |
10 |
4 |
0 |
1 |
0 |
| Two new case studies added to awesome-agent-failures repo
1. Microsoft 365 Copilot EchoLeak Zero-Click Prompt Injection… |
@vectara |
Company |
Original |
2025-12-01 |
404 |
11 |
3 |
0 |
2 |
0 |
| “Enterprise Deep Research: The Next Killer App for Enterprise AI”
Autonomous agents that can investigate your private … |
@vectara |
Company |
Original |
2025-11-26 |
916 |
16 |
3 |
1 |
2 |
0 |
| As your AI agents multiply, governance becomes the single point that keeps everything aligned with reality.
Enterprise… |
@vectara |
Company |
Original |
2025-11-26 |
381 |
13 |
2 |
1 |
2 |
0 |
| A few updates to our grounded hallucination leaderboard: Grok-4.1, GPT-5.1 and of course Claude Opus-4.5.
Repo: https:… |
@vectara |
Company |
Original |
2025-11-26 |
389 |
13 |
2 |
2 |
1 |
0 |
| NICSA (@NICSAnews) published a sharp breakdown of why governance is the backbone of AI in finance, outlining the risks,… |
@vectara |
Company |
Original |
2025-11-25 |
385 |
11 |
2 |
0 |
2 |
0 |
| Excited to share our new blog post, describing our research into agentic AI failure modes, and a novel benchmark for re… |
@vectara |
Company |
Original |
2025-11-24 |
476 |
10 |
3 |
0 |
3 |
0 |
| Agentic RAG shouldn’t require five disconnected tools and a maze of custom logic.
Vectara’s Agent OS brings everything… |
@vectara |
Company |
Original |
2025-11-20 |
596 |
11 |
3 |
0 |
3 |
0 |
| Since its release nearly two years ago, the @Vectara Hallucination Leaderboard served as the de-facto resource for unde… |
@vectara |
Company |
Original |
2025-11-20 |
610 |
12 |
4 |
0 |
3 |
0 |