Dify

Build Production-Ready Agentic Workflow

GitHub:

[Dify @dify_ai]

Built an AI workflow that actually runs part of a business? Get it on the Dify Marketplace Hottest Templates banner.

Dify Business Template Spotlight is live:
→ Publish an original business template to Creator Center
→ Every month we feature the hottest entries
→ Each featured template = 1 month of Dify Pro

Oct 30 – Jan 31 👇
https://t.co/qAD5D4Jozd

#DifyTemplates

[Dify @dify_ai]

Leadership Update: Dify Japan

Gen Watanabe (渡辺 元) has been appointed President and Representative Director of Dify’s Japanese subsidiary, LangGenius, K.K.
https://t.co/kcfotvisMb

[Dify @dify_ai]

Your AI app is for internal use. But can anyone access it? 🔐

IP Access Control is now available on Dify.

Set reusable IP allowlists, protect selected app access points, and check coverage in one place.

See how to set it up
https://t.co/aiNckDTEkV

#Dify #AIGovernance

[Dify @dify_ai]

Amazing energy in the room. Glad to be part of it! 🙌

[Emergences Labs @EmergencesLabs]

“The coding interview is dead!” We have turned the idea by @felixrieseberg at @AnthropicAI into a huge AI-Native Talent Hunt at SF Tech Week.

Don’t interview people about the work. Watch them do the work.

We believe hiring needs a better signal than LeetCode: Proof of Work with your PROCESS, a new credential in the AI era.

We made it happen with early believers in changing how AI-native talent is assessed and hired. Thank you to our amazing co-host @Tiny_Fish, agent partner @OpenAI Codex, and hiring partners @GenDigitalInc, @ZingageAI, @Gruve_ai, @cresta, @CreaoAI, @SmithfieldFoods, @dify_ai, @OpusClip, and @openart_ai.

Together with the enthusiasm of our candidates, we got:

• 1,600+ signups
• 300+ attendees
• 200+ submissions
• 10,000+ minutes working videos

How it works:
1. Companies turn internal business problems into real work sample tasks on NeoWork (https://t.co/wU6j5R3zkd).
2. Candidates tackle them on NeoHuman (https://t.co/NUCgk6WpGR) using Codex and other AI tools.
3. NeoWork evaluates the deliverable and recorded process. We highlight moments that reveal human judgment: catching an AI mistake, checking a claim before acting, or changing an approach that isn’t working.
4. Hiring managers review the work, our assessment, and supporting evidence to decide whom to interview or hire.

We grouped the 10 companies' works into 3 tracks: Product, Marketing, and Engineering. Each work was designed for about an hour. Examples include:

@GenDigitalInc: design a browser agent’s action pipeline that resists prompt injection.
@CreaoAI: turn design guidelines into enforceable rules and prove they catch real UI issues.
@cresta: build a support agent that follows policy and knows when to escalate.
@openart_ai: select consistent memories for an AI director.
@dify_ai: decide whether a support AI is ready to ship, backed by evidence.

Congratulations to our overall winners!

🥇 @samshanmukh: 97/100
🥈 Rohan R: 89/100
🥉 Shivam Mahajan: 87/100

And our track winners:
Product: Marcus Wong
Marketing: @AndrewDrok
Engineering: Akshat Patel

We know today’s job market is tough, even for people already in work:
- Juniors need experience to get experience.
- Career changers have skills their old titles don’t show.
- Laid-off professionals have to prove themselves all over again.
- Employed professionals must adapt to AI while keeping up with today’s workload.

That’s why we’ll keep hosting AI-Native Talent Hunts, with campus events at @UCBerkeley and @Stanford this November.

Follow our events calendar (https://t.co/ymW6qFAFAW) for your next chance to show what you can do.

[Photon @PhotonHQ]

Photon is now live on @dify_ai! 🚀

You can now bring iMessage, WhatsApp, telegram, email, and voice calling directly into your @dify_ai workflows.

Trigger workflows when someone sends an iMessage to your Photon line, use AI to understand their request, retrieve context from your knowledge base, and respond with an iMessage or even make a phone call.

[Dify @dify_ai]

Agent or Workflow? The answer depends on the job.

Too much autonomy can make AI harder to control. Too much structure can limit flexibility.

So how do you know which one to use? And what if you need both?

We explore this through a practical IT support scenario 👇
https://t.co/IKgnTdpdZf

#Dify #AIAgents #AIWorkflow

[Dify @dify_ai]

We’re hiring! Come meet a Dify Solution Architect tomorrow and learn what it’s like to work at Dify. We’re excited to see the different ways participants tackle the challenges with AI. #SFTechWeek

[Emergences Labs @EmergencesLabs]

The excitement is through the roof! 🚀

We’re hosting an AI-Native Talent Hunt during SF Tech Week with @OpenAI Codex and @Tiny_Fish. Cash prizes, Codex credits, opportunities to get hired.

Featuring real challenges from 10 companies:

TinyFish, @GenDigitalInc, @ZingageAI, @dify_ai, @Gruve_ai, @cresta, @CreaoAI, @SmithfieldFoods, @OpusClip, @openart_ai.

Approved attendees: bring your laptop + charger! See you all there.

#SFTechWeek

[Dify @dify_ai]

🎉 1,000+ plugins. 300+ templates.

Dify Marketplace keeps growing!

From search and RAG to multimodal tools, guardrails, and agent orchestration, more building blocks for AI applications are coming together.

Built by the community, for the community. 💙

Explore what’s possible. 👇
https://t.co/ytatkKan6j

[Dify @dify_ai]

@Tiny_Fish 300K and counting! Huge congrats to the TinyFish team! 🚀

[Dify @dify_ai]

When Jev’s fast decisions meet Dify’s workflow orchestration, live data turns into a visible, repeatable action loop.

In this demo, Dify transforms live MON/USDC order book data into structured signals for 20 rounds of paper trading with Jev. Every decision is logged and shown in charts, creating an app you can test, inspect, adapt, and publish.

Start building with Jev on Dify 👇https://t.co/jO8OZF0jDe

[Dify @dify_ai]

The latest Querit update brings automated web tracking to Dify, keeping your research workflows continuously updated with fresh competitor insights, industry news, and market trends. ⚡️

[Querit.ai @QueritAi]

Querit Monitors are now live on Dify 🔄

Search once. Monitor continuously.

Set up recurring searches, capture new results, and track what changes — all inside your Dify workflows.

From competitor tracking to news & research, let your agents keep watching while you move on.

🔗 https://t.co/ItVJaTF8Sj

#Querit #Dify

[Dify @dify_ai]

The IF Con Tokyo 2026 archive is now live.

We’re starting with the opening keynote by Luyu Zhang (@goocarlos), Founder & CEO of Dify: “Beyond AI Adoption — How to Redesign the Enterprise Workflow.”

Individual productivity and organizational productivity are not the same problem. Using the history of railway track gauges as a lens, the talk examines where the gap actually forms and lands on two things: handoffs and authority.

■ Two new announcements
- https://t.co/UDNbdMJtia
One endpoint for every model, removing the need to switch accounts, keys and billing every time you change models.

- Dify Knowledge Base 2.0
The most-used feature in Dify, redesigned from zero — removing the transfer between your documents and your agent.

Both are framed by the same question: which transfer does it remove?

■ Available now
- Digest (3 min) — the shape of the argument
- Full session (30 min) — the full case, including both announcements

Sessions from our sponsors and guest speakers will follow.
▶ https://t.co/iv1vm6bfN9

#IFConTokyo2026 #Dify #GenerativeAI #AIAgents

[Dify @dify_ai]

Take your Dify workflows beyond static knowledge. 🚀

The Glasser plugin connects external business data to your LLM nodes, helping your team add current market context to research, company analysis, and lead research.

Explore the integration 👇
https://t.co/IUW5xaGNE4

[Glasser @Glasserai]

You can now bring premium business data directly into your @dify_ai workflows with Glasser. Find contacts, research companies, and access search insights, all without leaving your workflow. https://t.co/ZSAEWmS1U0

[Dify @dify_ai]

Missed the new Dify Agent launch? Here’s the experience in two minutes.

Start with an idea, build through conversation, and test in Preview. Build once, then use it across the places your team works.

See how it comes together 👇
https://t.co/7tdJV3sWXz

#DifyNewAgent

[Dify @dify_ai]

@Glasserai Love this! Keep 'em coming 👏

[Dify @dify_ai]

Important Notice: Beware of Recruitment Scams

Dify has recently become aware of fraudulent websites and online accounts impersonating Dify and promoting fake job opportunities. These websites and accounts are not affiliated with or authorized by Dify.

Dify’s legitimate recruitment processes do not require candidates to top up an account, pay a deposit, advance funds, or transfer money. If someone claiming to represent Dify makes such a request, please stop communicating with them and do not share any personal or financial information.

For official job openings and application information, please refer only to the following channels:
Official careers page: https://t.co/RnPOg2mQau
Official LinkedIn page: https://t.co/paVIMdhYOs
Recruitment email: [email protected]

To report a suspicious recruitment website, account, or message, please contact our security team at [email protected].

Dify Team

[Dify @dify_ai]

“I’m looking for a housewarming gift under £40…” 🎁

For an ecommerce store, the challenge isn’t just showing customers what’s available. It’s helping them move from browsing to a confident decision.

So we put New Agent to work on a real homeware store. Starting with one simple task, we refined the same Agent through conversation as the business needs grew.

What started as product discovery became a more capable pre-sale experience.

Start with one real task. Build from there.

See how we did it 👇
https://t.co/VtQS8KdRIQ

#DifyNewAgent #Ecommerce #Dify

[Dify @dify_ai]

📢 Jev by @typesafeai is now available in Dify’s Question Classifier node. Use a model designed for structured decisions to route inputs across your workflow branches.

Try it in Dify 👇

[盐粒 Yanli @beautyyuyanli]

. @dify_ai
now supports to use Jev from TypeSafe AI in our classifier node!

[Dify @dify_ai]

A funny thing happens when your users become AI agents: your backend starts seeing a very different kind of traffic.

Agents don’t follow the rhythm of human users. They branch, retry, hold state, and can create bursts of concurrent traffic across your data layer.

That’s what we’ll explore in a Dify x TiDB fireside chat featuring Lusha Chen and Terry Purcell.

On September 24, 2026, from 11:00 AM–12:00 PM SGT, we’ll discuss what Dify is seeing as builders move from apps to agents, which data-layer assumptions start to break, and what teams need to rethink as agent workloads grow.

No slides. Just a focused conversation, followed by live Q&A.

Register here: https://t.co/7xDSuITxUP

#AIAgents #AgenticAI #AIInfrastructure #Dify #TiDB

[Dify @dify_ai]

@AIsaOneHQ Awesome work, AIsa team! Great to see the Dify ecosystem growing 🚀