Tigdukiduki, a Facebook page Oct – Nov 2026 Editor and producer
Three episodes of a Filipino explainer, made in Claude Code
A Taglish video series on why the Philippines stayed poor, made with a friend. I ran the scripts, the renders and the viewer tests in Claude Code, and kept the record of every step.
The problem
My friend Sai wrote a video series in Taglish, the everyday mix of Tagalog and English, on why the Philippines stayed poor while its neighbours grew. It follows the book Why Nations Fail. On 11 October 2026 he gave me his project files and I forked them, to see whether my Claude Code setup could make the episodes better.
Neither of us had made an explainer before. So every call had to be checked against something: a reader who had never seen the script, a source text, or the numbers from the last episode.
What I built
- Episode 1, “Bakit Hindi Umaasenso?”: 5 minutes 49 seconds, animated in code with HyperFrames, voiced by Sai, posted on 15 October.
- Episode 2, “Mula pa nung Kastila”: the script, rewritten nine times in Claude Code. Sai recorded it, built the cut and posted it on 2 November.
- Episode 3, “Ang lupa”: a new script, four rendered test openings and a panel of six simulated viewers, still in test on 12 November.
- A recording page: Sai reads one line at a time on his phone and the takes come back as files.
Every step below comes from the Claude Code session logs, the project files and our Linear board. Times are Philippine time.
Episode 1, from Sai’s script to the post
Episode 1 took 5 days, from my fork on 11 October to the post on 15 October.





1. The fork
At 4:29 am on 11 October I asked Claude Code to stress test Sai’s script. It ran 9 agents: 4 gathered facts and lessons, 2 rewrote, and 3 read both versions blind as a 24-year-old viewer in Dumaguete. The rewrite won all 3 reads. For Episode 1 the readers put the chance of finishing at 38% and 44%, against 29% and 33% for Sai’s.
2. A fix that made it worse
At 5:05 am I said we were skipping too many links between ideas. The next pass added them, so the script grew from 475 words to 710 and the readers’ chance of finishing fell from 55% to 40%. That showed the question was too wide, so I narrowed it to who had the power to block land reform.
3. Taglish, then four lenses
On 12 October I moved the script to everyday Taglish. Four lens passes (storytelling, teaching, facts and how the Taglish sounds) found 75 things and I applied 62. One was a date: Korea’s land reform law passed in June 1949, and the script said 1950. Then I cut the script from 662 words to 467.
4. First render in 11 minutes
At 3:00 am on 13 October I asked for the long version as a video. The first render was done at 3:11 am, 3 minutes 52 seconds long, with an ElevenLabs voice. By 5:11 am it had been through three rounds of fresh readers and one of them had checked the facts in the post.
5. The voice was rushed
At 1:33 pm I wrote that the voice felt rushed. Claude measured it: 168 words a minute, with 0.3 seconds between lines. I chose a slower voice setting with written pauses. It then offered to cut 24 lines of narration. I said no and asked for the animation to carry what the words could not, which gave the 4:43 cut.
6. A new narrator, then Sai
At 5:19 pm I heard that the slow voice was only the old voice slowed down, so we designed a new one. It said “lamang” with the wrong stress, which changes the word’s meaning, so that line was reworded. On 14 October at 8:07 pm Sai’s 51 recorded takes arrived and replaced the generated voice.
7. The clicks
I heard glitches in Sai’s takes and guessed we had sped them up. Claude found 73 clicks sitting on the joins between the small blocks of audio that the recording page saved. A new tool redrew the 109 joins in his takes, and the recording page was fixed before Episode 2.
8. Posted
The last cut is 5 minutes 48.7 seconds. Before it went out, a check confirmed that all 337 on-screen cues matched a spoken word and that no picture stayed up for less than 1.5 seconds. Sai shared the post at 1:03 am on 15 October.

Episode 2, nine versions of one script
For Episode 2 I worked on the script and Sai made the video.
1. Four lens walks
At 1:34 am on 23 October I asked for Sai’s 597-word draft to be stress tested. Four agents walked it, each with one lens: thinking tools, a model of how people at different stages hear an argument, a creator’s storytelling notes, and copywriting. They found 55 things, 2 of them blockers. The larger blocker: the middle of the script read as a fraud story, which fed the “corrupt” answer the episode argues against.
2. No more review documents
At 2:34 am I stopped the review document. I asked Claude to put each choice to me as a question with its own pick first, so I could confirm or correct in seconds. That became the rule for all my projects.
3. Thrown out and written again
At 5:54 pm I said the script was a sum of parts and not one piece. The rebuild around one question came to 45 lines. At 7:27 pm I said it was not worth saving. The next version was written from scratch around three moves the Spanish made (the chiefs, the tribute, the forced labour) and was ready at 7:52 pm.
4. Four more walks, then the recording page
Four more walks ran on the new script at 8:00 pm. After my answers it stood at 38 lines and 682 words. At 8:51 pm the recording page held Episode 2 next to Episode 1, with a comment box on every line.
5. Sai records and posts
Sai recorded 38 takes on 30 October, one for each line, then built the cut himself with real archive pages on screen. He posted it on 2 November at 5 minutes 49 seconds.

6. What the numbers said
On 29 October I read Episode 1’s numbers: the biggest drop came 9 seconds in. Four more walks said Episode 2 should open on its claim and move the recap later. I parked that advice that morning because the recording was not ready, and Episode 2 went out with the recap first. On 11 November it had 473 plays at 9 days and a 14.5-second average watch. Episode 1 had 913 plays at 28 days and 16.9 seconds.
Episode 3, testing the opening before recording
Episode 3 starts from what Episode 2 taught: the opening decides who stays.




1. A framework first
On 11 November at 4:54 am I said I would never reach an ending by picking between options, and asked for a framework. Eight agents studied the five channels I named and seven Filipino explainer creators. Twelve more turned that into a 13,000-word briefing. Its own machine checks failed on two of four counts, names and tone.
2. Where viewers leave
Claude pulled the page’s data and fitted a curve to each episode. About 58% of Episode 1’s plays and 68% of Episode 2’s ended before Facebook’s own graph begins. So the first three seconds became the thing to fix.
3. A panel of six
Six simulated viewers scored each opening blind. The real openings of Episode 1 and Episode 2 sat among the candidates, unlabelled, so the panel’s scores could be set against the real numbers. All six put Episode 1 above Episode 2, which matches the page. Sai’s recap opening came last.
4. The figure that lost
I wanted an Anatomy figure, a land office that turns village land into one owner’s title, as the first frame. Claude built it with 94 parts and proved it renders as video. The panel scored it 34.6%, and four of the six viewers read it as a gadget ad, so it moved inside the episode.

5. Four rendered openings
An audit of Sai’s script proposed 19 edits and I took each one. The new script has 44 lines. Four openings were rendered as silent 10-second clips. Claude caught that one of them put a line about friar estates over a photo of Hacienda Luisita, which was never a friar estate, and swapped the photo.
6. Undercooked
At 10:56 pm I called those openings undercooked. By 12:13 am I had the rule I was missing: if viewers do not understand us, we have already lost. That became four beats and six checks every opening must pass. Three more batches went to the panel that night. By 1:00 am on 12 November it had run 10 rounds, 60 viewer runs in all.
7. Where it stands
By that hour no opening had beaten Episode 1’s real 42% by more than the panel’s noise. The closest, “Titulo”, scored 40.7%, 43.7% and 39.9% in three rounds. The next step is a test on real viewers, with up to four openings, judged on views that last a minute.
The result
- Episode 1 had 913 plays, 10 shares and 9 new followers at 28 days. Episode 2 had 473 plays at 9 days. The page had 22 followers when I read the numbers on 11 November 2026.
- Six shorter reels cut from Episode 1 were rendered on 15 October and never posted.
- The method now lives in a playbook Sai and I both work from: ten steps to make a video, with reading the numbers as the last one.