design is not just how things look placement and consistency matter...
kcb just switched the position of "send to mobile" and "vooma" in their app and my muscle memory betrayed me, i tapped what i thought was send to mobile only to realize i had sent money to a vooma wallet instead of a number
small ui changes can have real consequences..
now im here waiting for an mpesa message that will never come and i have to look for an agent to withdraw it
@KCBInKenya I need a way to transfer my money from vooma to my mpesa
This series was a good one. The Playlist.
Here are some of the things I picked from this movie about startups.
1. Growth is the only language investors understand.
2. Control is always negotiated, never given.
3. Valuation is a story backed by traction.
4. Power shifts as soon as you take external money.
5. Fundraising is a trade-off, not a win.
6. Investors push for scale, sometimes at the expense of original ideals.
How to be a software developer in 2025 ?
- Frontend : Gemini 3 pro
- Backend : Claude Opus 4.5
- Database Design : Claude Sonnet
- Deployment : You
- Documentation : ChatGPT
- Security : Sentinel AI
- Project Manager : Perplexity
Prompt engineers make $120k–$300k/year.
And most people still use ChatGPT at 1% of its actual power.
That’s why I built “15000+ GPT-5 Prompts” - the biggest prompt vault you’ll ever need.
You get:
• 15000+ premium prompts
• High-converting frameworks
• Tips, tricks & hidden hacks
And for the next 72 hours… it’s 100% FREE.
To claim it:
1 Follow me @soni_jyoti_
2 Like + Repost
3 Comment “Send”
(I’ll DM it to you)
here is my personal developer productivity 'hack' 📌
I use GitHub issues as my personal task manager.
I opened a private GitHub repo and whenever an idea hits me, bug fix, feature thought, research topics, I just throw it into an issue.
so when I have a free moment, I browse through it and usually find something useful to work on.
simple, but it's been working well for me.
I’m coding until 4 AM again.
Not because I have to.
But because AI tools made me fall in love with building again.
After 15 years in management
I thought my coding days were behind me.
Then I discovered V0, Bolt, Cursor, Copilot, and Claude Code.
Built 7 apps + a startup in 10 months
All while keeping my full-time job
The difference between 2005 and 2025?
Then: 6 months to learn one framework
Now: 6 hours to build a working app
You didn’t miss the coding revolution.
You’re arriving at the perfect time.
The playing field just got leveled.
👉 If you’re coding (or thinking about it), I’d love to hear.
how i wished we could have lawyers for salary talks…they be like
“your honor, my client will not answer that question without proper compensation brackets disclosed first. We’ll need full disclosure of your budget before my client incriminates themselves” 😆😆😂
I get a lot of questions from people unsure how to actually find their footing in .NET.
I know it can feel overwhelming… not knowing whether to start with C# or .NET.
I'll be running a beginner-friendly session where I’ll try and simplify things. If interested, just comment.
You must know these 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗦𝘆𝘀𝘁𝗲𝗺 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄 𝗣𝗮𝘁𝘁𝗲𝗿𝗻𝘀 as an 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿.
If you are building Agentic Systems in an Enterprise setting you will soon discover that the simplest workflow patterns work the best and bring the most business value.
At the end of last year Anthropic did a great job summarising the top patterns for these workflows and they still hold strong.
Let’s explore what they are and where each can be useful:
𝟭. 𝗣𝗿𝗼𝗺𝗽𝘁 𝗖𝗵𝗮𝗶𝗻𝗶𝗻𝗴: This pattern decomposes a complex task and tries to solve it in manageable pieces by chaining them together. Output of one LLM call becomes an output to another.
✅ In most cases such decomposition results in higher accuracy with sacrifice for latency.
ℹ️ In heavy production use cases Prompt Chaining would be combined with following patterns, a pattern replace an LLM Call node in Prompt Chaining pattern.
𝟮. 𝗥𝗼𝘂𝘁𝗶𝗻𝗴: In this pattern, the input is classified into multiple potential paths and the appropriate is taken.
✅ Useful when the workflow is complex and specific topology paths could be more efficiently solved by a specialized workflow.
ℹ️ Example: Agentic Chatbot - should I answer the question with RAG or should I perform some actions that a user has prompted for?
𝟯. 𝗣𝗮𝗿𝗮𝗹𝗹𝗲𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Initial input is split into multiple queries to be passed to the LLM, then the answers are aggregated to produce the final answer.
✅ Useful when speed is important and multiple inputs can be processed in parallel without needing to wait for other outputs. Also, when additional accuracy is required.
ℹ️ Example 1: Query rewrite in Agentic RAG to produce multiple different queries for majority voting. Improves accuracy.
ℹ️ Example 2: Multiple items are extracted from an invoice, all of them can be processed further in parallel for better speed.
𝟰. 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗼𝗿: An orchestrator LLM dynamically breaks down tasks and delegates to other LLMs or sub-workflows.
✅ Useful when the system is complex and there is no clear hardcoded topology path to achieve the final result.
ℹ️ Example: Choice of datasets to be used in Agentic RAG.
𝟱. 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗼𝗿-𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗲𝗿: Generator LLM produces a result then Evaluator LLM evaluates it and provides feedback for further improvement if necessary.
✅ Useful for tasks that require continuous refinement.
ℹ️ Example: Deep Research Agent workflow when refinement of a report paragraph via continuous web search is required.
𝗧𝗶𝗽𝘀:
❗️ Before going for full fledged Agents you should always try to solve a problem with simpler Workflows described in the article.
What are the most complex workflows you have deployed to production? Let me know in the comments 👇
#LLM #AI #MachineLearning