Hang a weight from two ropes at angles and solve the tensions. The smallest real solver — and it carries its own proof: the three forces at the knot must sum to exactly zero, or it's wrong.
A weight W hangs from a knot held by two ropes — one to an anchor up and to the left at angle θ1 above horizontal, one up and to the right at θ2. Find the rope tensions T1 and T2. That's the whole problem — and it's the seed of every truss, cable, and free-body diagram you'll ever draw.
Two equations, two unknowns. At the knot the forces must balance:
ΣFx: −T1cosθ1 + T2cosθ2 = 0 ΣFy: T1sinθ1 + T2sinθ2 − W = 0Claude will set up and solve the linear system in a heartbeat. The point isn't the algebra — it's that you don't have to take the answer on faith. Statics hands you a free oracle: plug the tensions back in and the residual forces must be zero.
Drag the angles and the weight. The blue arrows are the rope tensions, the grey arrow is the weight; if the solution is right, the three arrows form a closed triangle — nothing left over.
Slide both angles toward horizontal and watch the tensions explode: as θ→0 the rope carries far more than the weight it holds (T ≈ W/2sinθ in the symmetric case). That's why a clothesline pulled “straight” can snap under a light load — the geometry, not the weight, sets the force.
A correct statics solution leaves no net force. You never have to wonder if the answer is right; you compute the residual and look.
Don't eyeball the tensions for plausibility — compute ΣFx and ΣFy with the answers plugged in. Zero means right. This residual check is the same oracle that scales up to a 30-member truss.
Pick a positive direction for x and y and keep it. The left rope pulls in −x; the right rope in +x; both pull +y; gravity is −y. Most wrong answers are a single flipped sign — which the residual catches instantly.
Two free levers worth setting. Turn the reasoning effort up
for the hard part — Claude Code's /effort (see
Feed it documents for the
model and effort controls); a transcription wants it low, an analysis like
this one wants it high. And end your prompt with an explicit
self-check — “before you finish, substitute the tensions back and confirm ΣFx and ΣFy are zero”
— which is exactly why the prompt above asks Claude to verify itself.
Naming the oracle is the highest-value line in the prompt. And keep the
expensive model's context light — route transcription and formatting
to cheaper tools (see Spend
tokens well).
The clean result is T1 = W·cosθ2 / sin(θ1+θ2) and T2 = W·cosθ1 / sin(θ1+θ2). At θ1=40°, θ2=55°, W=200 N: T1 ≈ 115 N, T2 ≈ 154 N. Substitute back and ΣFx = ΣFy = 0. Set both angles to 45° and each tension becomes 200 / (2·sin45°) = 141 N — matching W/(2sinθ). The answer proved itself; no grader required.
Same two moves — see explore in HTML, deliver in PDF.