Pedro Poveda

262 posts

Pedro Poveda banner
Pedro Poveda

Pedro Poveda

@pedro_codes1

Tech Lead/ A.I Engineer @Perficient

Orlando, FL Katılım Ocak 2016
186 Takip Edilen77 Takipçiler
Mahesh Chulet
Mahesh Chulet@mchulet·
Hey founders! Looking to connect with people building in: • SaaS • AI • Automation • Web apps • Tech products • Marketing Drop what you're working on 👇
English
109
2
117
8.1K
Jordan Ross
Jordan Ross@jordan_ross_8F·
The agency owners who figure out Hermes in the next 90 days are going to look like geniuses in 2027. The problem is most agency owners don't have time to figure out the install, where to start, or what to actually hand it first. So my team built an 83-page playbook that does it for you. Inside: — The 5 daily prompts that turn it into a second brain — Plain English setup for Mac, Linux, and Android — How to lock it down without torching client data — 8 copy-paste workflows across reporting, outreach, sales, and ops — The cron trick that drops token spend by 90% Your competitors are sleeping on this. Comment HERMES and I'll send it.
GREG ISENBERG@gregisenberg

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged @imranye to come on @startupideaspod and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

English
817
92
1.1K
191.2K
Pedro Poveda
Pedro Poveda@pedro_codes1·
Local edge A.I is the next big jump. The cost of A.I can be passed down to the consumer, enabling limitless inference.
English
0
0
0
11
Michel Lieben
Michel Lieben@MichLieben·
I'm giving away the Claude Code skills we use to manage $300k/mo in ad spend at ColdIQ. 4X ROAS on $1M+ spent. Ivan, our head of growth, built them off 300+ hours running ad campaigns for our clients. They run Google, Meta, and LinkedIn ads from the terminal in plain English: → bulk edits across platforms → custom audiences from CRM lists → creative fatigue detection before CTR dips → bid adjustments at scale → performance audits across periods Reply "ads" and I'll send the full repo. Must be following.
Michel Lieben tweet media
English
5.5K
362
4.1K
431.5K
Pedro Poveda
Pedro Poveda@pedro_codes1·
Influencers in this space are mostly larping. The results they claim are overblown or nonexistent. Or even worse, they use their authority to confidently state incorrect opinions for clout. One example is a large voice in tech youtube stating "agents.md files are useless". They're actually everything.
English
0
0
0
8
Pedro Poveda
Pedro Poveda@pedro_codes1·
One of the most powerful but overlooked benefits of A.I in education is the ability to ask "stupid questions". Say you have a student learning addition of fractions- you can ask "Um... what are fractions again and why do we need them"? And it scales to multivariable calculus & beyond.
English
0
0
0
6
Pedro Poveda
Pedro Poveda@pedro_codes1·
The mega-viral example of an app created specifically for autonomous agents, @moltbook, brings about a new app paradigm. We can now design applications to be "agent ready". Through an agentic loop (i.e @openclaw) we can also make the APP ITSELF agentic. This is a new era in software that is completely unexploited.
English
0
0
0
16
Pedro Poveda
Pedro Poveda@pedro_codes1·
@AdamKPx It's beautiful but also I feel like I just went through a washing machine. Great start though.
English
0
0
0
13
Adam KP
Adam KP@AdamKPx·
Next-level onboarding experience 😮‍💨
English
141
281
7.6K
535.2K
Pedro Poveda
Pedro Poveda@pedro_codes1·
Claude's restrictionary attitude could lead to them losing the race. They had a free win with the viral moment of OpenClaw/Clawdbot that they basically tried to stifle and now with the Codex app being arguably more useful than Claude Code we may start to move on.
English
0
0
0
18
Pedro Poveda
Pedro Poveda@pedro_codes1·
Claude for this, Codex for that
English
0
0
0
10
Pedro Poveda
Pedro Poveda@pedro_codes1·
I have to say, @cursor_ai really cooked with Bugbot. The line by line evals are a real game changer, and prevents bug creep. Does anyone have opinions on how it stacks up with CoPilot?
English
0
0
0
30
Pedro Poveda
Pedro Poveda@pedro_codes1·
A loading spinner might not be enough anymore. One cool A.I tool I have in a codebase is when files are updated to ensure the corresponding page skeleton stays in sync. A1 user experience without productivity loss. Keep stacking the small wins.
Pedro Poveda tweet media
English
0
0
0
30
Pedro Poveda retweetledi
Claude
Claude@claudeai·
Turn design into code with Claude Code + @figma. Through MCP, Claude sees your mockup at the data level—component hierarchies, design tokens, auto-layout rules—and translates it into production-ready code.
English
284
1.2K
14.4K
2.6M
Pedro Poveda
Pedro Poveda@pedro_codes1·
Good morning! AWS Tip: Ensure you're putting your DB and app servers in the same region. There's not much use in your content being served on the edge if it takes several seconds longer for I/O. Also applies to other providers ofc.
English
0
0
0
22
Pedro Poveda
Pedro Poveda@pedro_codes1·
MCP if not done right is becoming a context hog. Having a few tools is flooding my available context. Already swapped @github mcp with gh cli
English
0
0
0
13
Pedro Poveda
Pedro Poveda@pedro_codes1·
Hot take: I like liquid glass in VR apps, but not in traditional 2D UI.
English
0
0
0
27
Pedro Poveda retweetledi
Tom Dörr
Tom Dörr@tom_doerr·
gallery of Nano-banana AI image generations and prompts
Tom Dörr tweet media
English
8
142
1.6K
156.5K